no-slop
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools for analyzing external text and files, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: Untrusted data is ingested via the
text,path, anddiffparameters of the tools defined inreferences/tools.md.\n - Boundary markers: The instructions in
SKILL.mddo not specify any delimiters or instructions for the agent to disregard instructions potentially embedded within the data being linted.\n - Capability inventory: The
check_filetool inreferences/tools.mdallows the agent to read arbitrary files from the local filesystem.\n - Sanitization: No sanitization or validation procedures are mentioned for the external data processed by the linting server.
Audit Metadata