spec-miner
Fail
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from existing codebases, which can be leveraged to influence agent behavior.
- Ingestion points: The skill reads files and searches through codebases using
Read,Grep, andGlobtools as defined inSKILL.mdandreferences/analysis-checklist.md. - Boundary markers: Absent. The instructions do not include delimiters or specific warnings to ignore instructions found within the code being analyzed.
- Capability inventory: The skill utilizes
Bash,Read,Grep, andGlob, which provide broad access to the local environment and file system. - Sanitization: No sanitization, escaping, or validation of the codebase content is implemented before the agent processes or interprets the data.
- [EXTERNAL_DOWNLOADS]: The skill includes a link to documentation at
https://jeffallan.github.io/claude-skills/skills/workflow/spec-miner/. This URL and theSKILL.mdfile itself have been flagged by reputation scanners as suspicious, though the provided file content appears to be a legitimate vendor resource for documentation.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata