api-shape-explorer
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted user input and incorporates it directly into the instructions for secondary agents.
- Ingestion points: Untrusted requirements and module descriptions are gathered from the user in Step 1 and used in Step 2 within
SKILL.md. - Boundary markers: There are no boundary markers or delimiters used in the prompt template to separate the user's input from the system instructions.
- Capability inventory: The skill leverages the
Tasktool to initiate sub-agent execution, which can be influenced by the injected content. - Sanitization: No input sanitization or filtering is performed on the data before it is passed to the sub-agents.
Audit Metadata