reflect
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection where the agent might process instructions hidden in the codebase.
- Ingestion points: The instruction in SKILL.md to "explore the codebase" to answer questions allows the agent to ingest untrusted data from project files.
- Boundary markers: The skill lacks instructions or delimiters to isolate or sanitize content read from the codebase.
- Capability inventory: The agent uses its built-in file-reading and search capabilities to access the codebase.
- Sanitization: No sanitization or filtering is applied to the data retrieved during the codebase exploration.
Audit Metadata