api-shape-explorer
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied module descriptions and requirements which are interpolated into prompts for parallel sub-agents. This creates a standard surface for indirect prompt injection where user input could attempt to influence sub-agent behavior.
- Ingestion points: User-provided text in the 'Gather Requirements' step within
SKILL.mdis ingested into the agent context. - Boundary markers: User input is placed into placeholders (e.g.,
[module description]) without the use of strict delimiters or specific instructions to ignore embedded commands. - Capability inventory: The skill's actions are restricted to spawning sub-agents for text generation via the
Tasktool; it does not request or use tools for network access, file system modification, or shell execution. - Sanitization: No input sanitization, filtering, or validation is performed on the user-provided requirements before interpolation.
Audit Metadata