effect-development
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and follow patterns from local documentation files (LLMS.md, ai-docs/src). This represents an attack surface where instructions embedded in those files could influence agent behavior.
- Ingestion points: LLMS.md and the ai-docs/src directory.
- Boundary markers: No delimiters or safety instructions are provided to the agent to treat documentation as non-executable data.
- Capability inventory: The agent is expected to identify APIs and apply guidance found in documentation to code implementation.
- Sanitization: No validation or sanitization of the documentation content is performed before processing.
- [NO_CODE]: The skill consists only of instructions in SKILL.md and does not include any executable scripts or configuration files.
Audit Metadata