Error Handling Auditor
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill possesses an attack surface for instructions embedded within analyzed code.
- Ingestion points: External source code files accessed via 'Read' and 'Grep' tools in SKILL.md.
- Boundary markers: Absent. The instructions do not define delimiters to separate trusted instructions from the code being processed.
- Capability inventory: The 'Edit' tool allows the agent to perform write operations on the filesystem, which could be subverted by malicious code comments.
- Sanitization: Absent. There is no logic to filter or ignore natural language instructions found within string literals or comments in the audited codebase.
Recommendations
- AI detected serious security threats
Audit Metadata