wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to integrate information from
CONTEXT.mdandCONTEXT-MAP.md, which creates an attack surface for indirect prompt injection if those files contain malicious instructions. - Ingestion points: References to
CONTEXT.mdandCONTEXT-MAP.mdinSKILL.md. - Boundary markers: Absent; there are no instructions to delimit the file content or ignore embedded commands.
- Capability inventory: None; the skill has no shell execution, file writing, or network access capabilities.
- Sanitization: Absent; the skill does not specify any validation or filtering of the content read from the files.
Audit Metadata