technical-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRE C T_PRO M P T_INJE C T ION]: The skill analyze s untruste d codebase file s, creatin g a vunerability surface for indirect prompt injection.
- Ingestion points: Use s Read, Grep, and Glob tool s to retrieve content from file s with in the workspace.
- Boundary marker s: No explicit delimiter s or instruction s are provide d to isolate natural language instruction s embedde d with in the code it analyze s.
- Capability inventor y: The agent has acces s to file readin g tool s and git command execution via Bash(git:*) as specifie d in the allowe d-tool s field.
- Sanitization: The re are no mechanism s for sanitizin g or filterin g content from the codebase before processin g it for technical analysis.
Audit Metadata