cr-request
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from source code diffs, repository files, and external issue trackers, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted data is ingested from Git diffs, untracked files, and linked issue text as described in SKILL.md and references/target.md.
- Boundary markers: The skill includes specific instructions to treat all ingested text as data rather than instructions, which serves as a mitigation strategy (SKILL.md, references/brief.md).
- Capability inventory: The skill uses read-only Git commands and dispatches isolated sub-agents for analysis, limiting the potential impact of an injection (SKILL.md, references/target.md).
- Sanitization: No explicit sanitization or filtering of the ingested content is defined.
Audit Metadata