assigns-audit
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local Elixir source code, creating an attack surface for indirect prompt injection where malicious instructions could be embedded in code comments or data.
- Ingestion points: Source files defined by the user argument (SKILL.md).
- Boundary markers: No delimiters are specified to separate untrusted file content from the agent's instruction set.
- Capability inventory: Access to
Read,Grep,Glob, andBashtools allows for comprehensive file inspection (SKILL.md). - Sanitization: The skill does not specify methods for sanitizing or filtering input from the audited files.
Audit Metadata