data
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it displays untrusted strings and binary data to the agent.
- Ingestion points: Data is ingested through the
stringstable andbytes()functions inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions to ignore instructions contained within the data.
- Capability inventory: The skill has access to the
BashandGreptools as specified in theSKILL.mdfrontmatter. - Sanitization: No sanitization or validation of the binary content is performed.
Audit Metadata