bento-investigate
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow instructions from repository-level files such as
AGENTS.md,CLAUDE.md, and a specific overlay file.agents/bento/bento-investigate.md. This creates an attack surface where a malicious repository could provide instructions that influence agent behavior during the investigation process.\n - Ingestion points: Reads
.agents/bento/bento-investigate.md,AGENTS.md, andCLAUDE.mdfrom the workspace root.\n - Boundary markers: Absent. Instructions from workspace files are integrated directly into the agent context.\n
- Capability inventory: The skill relies on standard agent tools for file reading, grep searching, and command execution for tests.\n
- Sanitization: Absent. Content from external repo files is adopted without prior validation.\n- [NO_CODE]: The skill consists entirely of instructional markdown and does not include any scripts, executables, or dynamic execution contexts.
Audit Metadata