The static findings are documentation false positives from Markdown inline code, fenced examples, and relative links. The Firecrawl command examples match the skill purpose, and no prompt injection, credential exfiltration, or hidden file access was found in SKILL.md.
The static findings are documentation false positives from Markdown inline code, fenced examples, and relative links. The Firecrawl command examples match the skill purpose, and no prompt injection, credential exfiltration, or hidden file access was found in SKILL.md.
The skill intentionally grants Bash access to Firecrawl CLI commands that crawl user supplied URLs and write results to local files. The static weak cryptography, Ruby backtick, and path traversal alerts are false positives in Markdown descriptions and links, but the intended network crawling and output file behavior warrant a medium risk warning. No evidence found of prompt injection, credential exfiltration, hidden scripts, or malicious intent.
1
Files scanned
59
Lines analyzed
6
Review items
3
False positives ignored
Capability review items (3)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
TRUE_POSITIVE: The skill allows Bash execution of firecrawl and npx firecrawl commands, then shows commands that crawl user supplied URLs. This is legitimate for the skill purpose, but it can access external sites and should be used only with authorized targets.
The allowed-tools block explicitly permits Firecrawl CLI execution, and the quick start shows crawl commands. The behavior is intentional and documented, with no evidence of hidden command construction.
TRUE_POSITIVE: The examples crawl a placeholder URL and describe bulk extraction from many pages. This creates normal web crawling risk, including accidental crawling of unauthorized, private, or high cost targets.
The skill purpose and command examples clearly require network crawling. The risk depends on user target selection, so this is elevated but not malicious.
TRUE_POSITIVE: The documented commands write crawl results with -o, and the options table exposes --output <path>. A careless output path could overwrite local files or place crawl data in an unintended location.
The output path option is explicitly documented, but there is no wrapper code that expands or modifies paths. The practical risk is from user choice rather than malicious implementation.
Static false positives ignored (3)
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.
Markdown Backticks Misclassified as Shell Execution
FALSE_POSITIVE: The static Ruby or shell backtick alerts are Markdown inline code, command examples, or option names. They are documentation text, not Ruby execution syntax.
The flagged text appears inside Markdown bullets, fenced code blocks, and a Markdown table. SKILL.md contains no Ruby source or dynamic shell interpolation.
Relative Documentation Links Misclassified as Path Traversal
FALSE_POSITIVE: The ../ sequences are Markdown links to nearby skill documentation. They are not used as runtime file paths and do not read or write the filesystem.
The entire evidence is in the See also section as links to other SKILL.md files. There is no command or code path that consumes these links.
FALSE_POSITIVE: The flagged lines contain front matter description text and a Markdown table header. No hashing, encryption, cipher selection, or cryptographic API appears in the file.
Manual review found no cryptographic operation at the reported locations or elsewhere in SKILL.md. The static detector matched unrelated prose or formatting.
Security review of firecrawl-crawl skill completed. Static analysis flagged multiple patterns (external_commands, filesystem path traversal, weak_crypto, network_reconnaissance) that were all evaluated as false positives. The flagged content consists of documentation examples in markdown code blocks and relative markdown links to other skill files, not actual security risks. The skill is a legitimate web scraping tool that uses the firecrawl CLI to crawl and extract content from websites.
1
Files scanned
59
Lines analyzed
0
Review items
2
False positives ignored
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.
Static analyzer flagged bash command examples in SKILL.md as 'external_commands'. These are documentation examples in markdown code blocks showing how to use the firecrawl CLI, not actual code execution. No command injection risk exists in this documentation file.
Markdown documentation file contains bash command examples in code blocks - standard skill documentation format with no actual code execution
Static analyzer flagged relative path references in markdown links as 'path traversal'. These are valid relative links to other skill documentation files (e.g., '../firecrawl-scrape/SKILL.md'), which is standard documentation cross-referencing, not filesystem access.
Markdown relative links to documentation files are standard documentation practice, not filesystem operations
No confirmed security findings were recorded for this completed audit.