context
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external repository files including
docs/glossary.md, ADRs, and source code, creating a surface for indirect prompt injection. 1. Ingestion points:docs/glossary.md,docs/adr/,docs/decisions/, repository instructions, and source code. 2. Boundary markers: Absent. 3. Capability inventory: Modification of theCONTEXT.mdfile. 4. Sanitization: Absent.\n- [NO_CODE]: The skill does not include any executable scripts, binaries, or package dependencies.
Audit Metadata