sounding
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from the local project environment, which could be manipulated to influence the agent's decision-making process.
- Ingestion points: The skill instructs the agent to read git history, issue trackers, documentation, notes, and local session history in
SKILL.md. - Boundary markers: No specific delimiters or warnings are provided to help the agent distinguish between its instructions and potentially malicious content within the analyzed project files.
- Capability inventory: The skill allows for read-only system commands and possesses the authority to recommend the execution of other installed skills.
- Sanitization: There are no instructions to sanitize, filter, or validate the content retrieved from the project sources.
- [SAFE]: No evidence of malicious code, network exfiltration, or persistence mechanisms was detected. The skill contains no executable scripts and explicitly restricts the agent to advisory and read-only operations.
Audit Metadata