invention-structuring
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: User-provided
$ARGUMENTSand local files includingpatent/INVENTION_BRIEF.md,patent/PRIOR_ART_REPORT.md, andpatent/NOVELTY_ASSESSMENT.md(documented in the 'Inputs' section of SKILL.md). - Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings for the ingested content.
- Capability inventory: The skill is configured with broad tool access including
Bash(*),Write,Edit, andmcp__codex__codex(specified in the YAML frontmatter). - Sanitization: There is no evidence of filtering, escaping, or validation of the input data before it is processed or passed to the external
mcp__codex__codextool in Step 6.
Audit Metadata