code-search
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a research tool for identifying GitHub implementations. No malicious code, prompt injections, or unauthorized data access patterns were identified in the workflow or documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from external sources (GitHub), which is an ingestion point for untrusted content.
- Ingestion points: External GitHub search results fetched via WebSearch and GitHub API as described in SKILL.md.
- Boundary markers: None explicitly mentioned in the documentation for separating ingested data from instructions.
- Capability inventory: No dangerous capabilities such as file system writes, arbitrary shell command execution, or network exfiltration of local data were identified in the skill scripts or workflow.
- Sanitization: The workflow describes parsing search results into structured Finding objects (containing name, URL, and stars), which minimizes the risk of raw content influencing the agent.
Audit Metadata