stitch-sdk-readme
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes source code files and JSON metadata from the repository to generate documentation, which creates a surface for instructions embedded in those files to influence agent output or actions.\n
- Ingestion points: The skill is instructed to read various TypeScript source files (e.g.,
packages/sdk/src/index.ts,sdk.ts,project.ts) and generated metadata (domain-map.json,tool-definitions.ts) from thepackages/sdk/directory.\n - Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions embedded in the source data.\n
- Capability inventory: The skill utilizes file reading tools to ingest the codebase and generates text for the README file.\n
- Sanitization: There is no evidence of sanitization, filtering, or validation of the extracted API information before it is processed by the model.
Audit Metadata