find-animation-opportunities
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: A deterministic detector flagged instructions in sections/hard-rules.md (Rule 4) regarding the ignoring of previous instructions. Review of the context shows this is a defensive instruction requiring the agent to disregard instructions found within data files (source code), which is a recommended security practice to prevent external manipulation.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing untrusted source code, which is a potential vector for indirect prompt injection. Ingestion points: The skill identifies and reads repository content to find animation opportunities, as specified in Workflow.md and Where to Hunt.md. Boundary markers: Defensive instructions are present in sections/hard-rules.md (Rule 4) to explicitly treat repository content as data and not instructions. Capability inventory: The skill is functionally restricted to read-only reporting and does not have the ability to execute code, perform network operations, or write to the file system. Sanitization: The skill employs instruction-level boundaries to prevent the agent from acting on content discovered within the analyzed codebase.
Audit Metadata