quality-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest and evaluate external skill files. This creates an indirect prompt injection surface where malicious instructions embedded in the audited content could influence the AI agent's assessment or report generation.
- Ingestion points: External skill content processed during Phase 2 (Content Evaluation) and via the audit workflow.
- Boundary markers: The skill does not define specific delimiters or instructions to treat the audited content as data rather than instructions.
- Capability inventory: Includes shell command execution via the cortex CLI and potential file modification when using the
--fixflag. - Sanitization: No explicit sanitization or escaping of the ingested skill content is documented.
- [COMMAND_EXECUTION]: The skill documents and uses several CLI commands (
cortex skills audit) to perform its functions. While these appear to be standard platform tools, they represent shell execution capabilities that could be misused if command arguments are not properly handled.
Audit Metadata