identify-assumptions-existing
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data via the
$ARGUMENTSplaceholder and external files (designs, PRDs, research) to perform its analysis. This creates a surface where malicious instructions within that data could attempt to influence the agent's behavior. - Ingestion points:
$ARGUMENTSvariable and file reading instructions inSKILL.md. - Boundary markers: The skill does not use specific delimiters or instructions to ignore potential commands within the user's input.
- Capability inventory: The skill consists solely of markdown instructions and does not possess capabilities for file writing, network requests, or command execution.
- Sanitization: No sanitization or validation of the input data is performed by the skill itself.
Audit Metadata