harden
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (git diffs, source code, specs, etc.) which provides a surface for indirect prompt injection.\n
- Ingestion points: The skill ingests user-provided targets (git diffs, source modules, specs, etc.) and explores the surrounding project files as described in
SKILL.md.\n - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the content of the target files to distinguish them from system instructions.\n
- Capability inventory: The skill describes workflows involving file exploration and agent orchestration (subagents) to process the target content.\n
- Sanitization: There are no mentioned mechanisms to sanitize or validate the content of the ingested target files before processing.
Audit Metadata