bento-figure-it-out
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
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 repository-specific overlay files (e.g.,.agents/bento/bento-figure-it-out.md). These files are part of the external environment and could contain malicious instructions designed to hijack the agent's behavior. - Ingestion points: Instructions in
SKILL.mdexplicitly direct the agent to load and follow content fromAGENTS.md,CLAUDE.md, and.agents/bento/bento-figure-it-out.md. - Boundary markers: The skill lacks explicit boundary markers or instructions to treat the content of these files as untrusted data, instead stating to "follow it".
- Capability inventory: As a fallback skill for "off-catalog" tasks, the agent may utilize any available tools (such as file system operations or command execution) to fulfill instructions found in the ingested files.
- Sanitization: There is no mention of sanitization, validation, or filtering of the instructions loaded from the repository files.
Audit Metadata