Audit History
api-dev - 9 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v9 Latest | Jul 5, 2026, 03:56 AM | 1 confirmed | 0 | No capability change |
| v8 | Jul 5, 2026, 03:56 AM | 1 confirmed | 0 | External commandsEnv variables |
| v7 | Jun 28, 2026, 01:01 PM | 2 confirmed | 3 | External commandsEnv variables |
| v6 | Jan 16, 2026, 06:27 PM | No confirmed findings | 1 | No capability change |
| v5 | Jan 16, 2026, 06:27 PM | No confirmed findings | 1 | No capability change |
| v4 | Jan 16, 2026, 06:27 PM | No confirmed findings | 0 | Network accessExternal commandsEnv variables |
| v3 | Jan 10, 2026, 10:55 AM | No confirmed findings | 0 | No capability change |
| v2 | Jan 10, 2026, 10:55 AM | No confirmed findings | 0 | No capability change |
| v1 | Jan 10, 2026, 10:55 AM | No confirmed findings | 0 | Baseline |
Jul 5, 2026, 03:56 AM
Most static findings are false positives from Markdown code fences, placeholder URLs, request object names, and Redis URL parameters in examples. One critical issue is confirmed: the caching example deserializes Redis data with pickle.loads, which can enable code execution if cache data is controlled or poisoned. No prompt injection or malicious marketplace intent was found.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (15)
🌐 Network access (11)
🔑 Env variables (8)
Detected Patterns
Jul 5, 2026, 03:56 AM
Most static findings are false positives from Markdown code fences, placeholder URLs, request object names, and Redis URL parameters in examples. One critical issue is confirmed: the caching example deserializes Redis data with pickle.loads, which can enable code execution if cache data is controlled or poisoned. No prompt injection or malicious marketplace intent was found.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (15)
🌐 Network access (11)
🔑 Env variables (8)
Detected Patterns
Jun 28, 2026, 01:01 PM
Static command-execution findings are false positives from Markdown code fences, and credential-access findings are Redis URL examples rather than environment reads. The skill is documentation-only, but it includes an unsafe pickle deserialization cache pattern that should be warned about before publication.
Confirmed security concerns (2)
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.
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.
Risk Factors
Detected Patterns
Jan 16, 2026, 06:27 PM
Pure documentation skill containing example code patterns for API development. Static scanner flagged standard patterns (HTTP clients, connection strings, pickle serialization) as suspicious, but these are legitimate examples in documentation. No malicious intent found. Original audit correctly rated this skill safe.
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.
Risk Factors
🌐 Network access (11)
⚙️ External commands (15)
🔑 Env variables (10)
Jan 16, 2026, 06:27 PM
Pure documentation skill containing example code patterns for API development. Static scanner flagged standard patterns (HTTP clients, connection strings, pickle serialization) as suspicious, but these are legitimate examples in documentation. No malicious intent found. Original audit correctly rated this skill safe.
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.
Risk Factors
🌐 Network access (11)
⚙️ External commands (15)
🔑 Env variables (10)
Jan 16, 2026, 06:27 PM
Pure documentation skill containing example code patterns for API development. Static scanner flagged standard patterns (HTTP clients, connection strings, pickle serialization) as suspicious, but these are legitimate examples in documentation. No malicious intent found. Original audit correctly rated this skill safe.
Risk Factors
🌐 Network access (11)
⚙️ External commands (15)
🔑 Env variables (10)
Jan 10, 2026, 10:55 AM
This is a pure documentation skill containing only markdown content with code examples. The skill does not execute any code, access filesystem, read environment variables, or make network requests. All code blocks are example patterns for API development that would run in the user's own environment.
Jan 10, 2026, 10:55 AM
This is a pure documentation skill containing only markdown content with code examples. The skill does not execute any code, access filesystem, read environment variables, or make network requests. All code blocks are example patterns for API development that would run in the user's own environment.
Jan 10, 2026, 10:55 AM
This is a pure documentation skill containing only markdown content with code examples. The skill does not execute any code, access filesystem, read environment variables, or make network requests. All code blocks are example patterns for API development that would run in the user's own environment.