stories
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from research files, representing a potential injection surface, though no exploitable capabilities are present.\n
- Ingestion points: Processes the content of
docs/<feature>/research.md(Step 1 of the Process section).\n - Boundary markers: Absent; the skill does not instruct the agent to distinguish between data and potential instructions within the ingested file.\n
- Capability inventory: Limited to reading and writing local documentation files. No network operations, subprocess executions, or dynamic code loading are identified.\n
- Sanitization: No sanitization or validation of the ingested research content is performed before it is used to generate the output file.
Audit Metadata