source-driven-development
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and acting upon untrusted external data, such as framework documentation and screenshots, which can influence the agent's code implementation and command execution. Ingestion points: The process in 'references/current-guidance.md' involves reading external documentation, SDKs, APIs, and screenshots. Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions in external sources. Capability inventory: The skill guides the agent to perform repository code edits and execute verification commands. Sanitization: Absent; the instructions do not specify any validation or sanitization of content from external sources.
- [NO_CODE]: The skill consists entirely of markdown documentation and contains no executable scripts or binary files.
Audit Metadata