debug-retro
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes conversation history from a debugging session, which represents an untrusted data ingestion surface.
- Ingestion points: Processes conversation logs to identify human interventions (SKILL.md).
- Boundary markers: No explicit delimiters are defined to separate the data from the agent's instructions.
- Capability inventory: The skill is capable of writing to project files, specifically
.claude/debug-layers.mdandCLAUDE.md. - Sanitization: The risk is mitigated by a mandatory user-approval checkpoint ("Ask the user to approve the rows by number. Write only the approved rows"), ensuring the user reviews and validates all generated content before it is committed to the file system.
- [EXTERNAL_DOWNLOADS]: The skill mentions the author's public repository (
github.com/rajnandan1/sharper-skills) as a destination for proposing skill improvements via issues or pull requests.
Audit Metadata