dev-feature-lite
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest external, untrusted content from the repository (code, tests, and repository-specific instructions), which provides a surface for indirect prompt injection attacks.
- Ingestion points: SKILL.md instructs the agent to read repository instructions, affected code, tests, and existing patterns.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the read files are provided.
- Capability inventory: The agent is authorized to search the filesystem, read/write code, and execute local test suites/tools.
- Sanitization: No sanitization or filtering logic is defined for the ingested data.
Audit Metadata