sherpy-flow
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (an initial requirements document) during Step 1 of the workflow.
- Ingestion points: Processes any
.md,.txt, or.docxfile found in the project directory as an 'initial requirements document' for Gap Analysis (SKILL.md). - Boundary markers: There are no instructions to use delimiters or 'ignore embedded instructions' warnings when reading the content of the requirements document.
- Capability inventory: The skill has the capability to scan directories, create folders, write files, and invoke other specialized skills based on the content of the documents.
- Sanitization: No sanitization or validation of the document content is performed before it is passed to the analysis skill.
Audit Metadata