ln-614-docs-fact-checker
Fail
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs and executes shell commands using variables derived from untrusted project documentation. As documented in
references/claim_extraction_rules.md, values such as$path,$VAR,$name,$file, and$lineare interpolated into shell utilities includingls,grep, andsed. This behavior creates a risk of command injection if the source documentation contains shell metacharacters.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface.\n - Ingestion points: Documentation files (.md) across the entire project.\n
- Boundary markers: Not utilized.\n
- Capability inventory: Shell command execution via the
Bashtool and file system access viaRead,Grep, andGlob.\n - Sanitization: No evidence of sanitization or input validation for extracted claim values prior to their use in system commands.\n- [EXTERNAL_DOWNLOADS]: The file
diagram.htmlfetches themermaid.min.jslibrary fromcdn.jsdelivr.net, which is a well-known and established content delivery network.
Recommendations
- AI detected serious security threats
Audit Metadata