anti-slop
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code to identify slop patterns. It fails to use explicit boundary markers or delimiters when presenting these file contents to the agent, potentially allowing instructions embedded in the code to influence the agent's behavior. Ingestion points: File content reading in Step 3 of SKILL.md. Boundary markers: Absent. Capability inventory: File system read and shell command execution via grep. Sanitization: None.
- [COMMAND_EXECUTION]: The workflow involves using the grep command to search for function and export usage across the codebase. While intended for cross-file auditing, executing shell commands based on symbols parsed from untrusted source code is a sensitive operation.
Audit Metadata