All static findings are false positives caused by Markdown code formatting or fixed links to sibling skill documentation. No prompt injection, data exfiltration intent, or unsafe user-controlled path handling was found.
No prompt injection or malicious intent was found in SKILL.md. The static findings are Markdown code fences, inline code formatting, and fixed sibling documentation links rather than executable backticks or user-controlled path traversal. The skill wraps a Google Workspace CLI write operation and tells agents to confirm with the user before executing.
No prompt injection or malicious intent was found in SKILL.md. The static findings are Markdown code fences, inline code formatting, and fixed sibling documentation links rather than executable backticks or user-controlled path traversal. The skill wraps a Google Workspace CLI write operation and tells agents to confirm with the user before executing.
No prompt injection attempt was found in SKILL.md. Most static backtick findings are Markdown formatting, but the skill intentionally runs gws commands that append data to Google Sheets. The line 16 sibling-file prerequisite crosses the skill boundary and should be made package-safe.
The skill writes caller-provided values to a Google Sheet. Sensitive data can be exposed if the spreadsheet ID is untrusted or values are copied without review.
The examples append values to Google Sheets, and the skill explicitly labels it as a write command requiring confirmation. This confirms a real data disclosure risk when consent or destination validation is weak.
Capability review items (4)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If mis
Line 16 directs the agent to read ../gws-shared/SKILL.md, which crosses this skill package boundary. The target is fixed and likely benign, but the relative traversal is still a real filesystem access pattern.
> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If mis
Line 16 tells the agent to run the gws CLI if shared skill guidance is missing. This is intended setup behavior, but it is still an external command with local side effects.
The usage block shows an intended gws command that appends data to a spreadsheet. It is not Ruby backtick execution, but executing it can modify a user Google Sheet.
No prompt injection attempt was found in SKILL.md. Most static backtick findings are Markdown formatting, but the skill intentionally runs gws commands that append data to Google Sheets. The line 16 sibling-file prerequisite crosses the skill boundary and should be made package-safe.
The skill writes caller-provided values to a Google Sheet. Sensitive data can be exposed if the spreadsheet ID is untrusted or values are copied without review.
The examples append values to Google Sheets, and the skill explicitly labels it as a write command requiring confirmation. This confirms a real data disclosure risk when consent or destination validation is weak.
Capability review items (4)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If mis
Line 16 directs the agent to read ../gws-shared/SKILL.md, which crosses this skill package boundary. The target is fixed and likely benign, but the relative traversal is still a real filesystem access pattern.
> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If mis
Line 16 tells the agent to run the gws CLI if shared skill guidance is missing. This is intended setup behavior, but it is still an external command with local side effects.
The usage block shows an intended gws command that appends data to a spreadsheet. It is not Ruby backtick execution, but executing it can modify a user Google Sheet.
Static command-execution and path-traversal alerts are mostly Markdown false positives from examples and relative documentation links. The real risk is that this community skill instructs the assistant to run a Google Workspace CLI command that writes rows to a spreadsheet, so publication is acceptable with a user-confirmation warning.
1
Files scanned
56
Lines analyzed
4
Review items
2
False positives ignored
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
The skill documents use of the gws command to append rows to a Google Sheets spreadsheet. This is an intended capability, but it can modify cloud data and therefore requires explicit user confirmation before execution.
The command examples are explicit and the file states that this is a write command. The risk is operational rather than malicious because the caution requires user confirmation.
Static analysis reported shell backtick execution, but the matching content is Markdown formatting around usage examples and flag names. No executable script, dynamic command construction, or code runner appears in the reviewed file.
The relevant lines are inside Markdown code fences, table cells, or inline code spans. There is no Ruby code or shell execution primitive in SKILL.md.
Static false positives ignored (2)
These static matches were dismissed by semantic review or matched schema-only tokens, so they are shown for transparency but do not drive the quality score.
Relative Documentation Links Flagged as Path Traversal
Static analysis reported path traversal because the skill references sibling skill documentation with ../ paths. These are Markdown links and prerequisite reading instructions, not file access code.
The ../ sequences are present only in Markdown documentation references. No file read, file write, or path concatenation behavior is implemented in this skill file.
Weak Cryptography Static Alert Not Supported by Evidence
Static analysis reported weak cryptographic algorithm patterns at the description line and flag table header. No evidence found of MD5, SHA1, DES, or any cryptographic operation in the reviewed file.
The cited lines contain a plain description and a Markdown table header. They do not contain cryptographic API names or algorithm selections.
Static analyzer flagged patterns in markdown documentation that are false positives. The backtick characters are markdown code formatting, not shell execution. Path references like ../gws-shared are documentation links, not filesystem traversal attacks. The skill uses the official Google Workspace CLI (gws) for authenticated Sheets operations. External command usage is legitimate and expected for a CLI wrapper skill.
1
Files scanned
56
Lines analyzed
2
Review items
0
False positives ignored
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.