ai-slop-detector
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides specific Perl and grep command templates for the agent to use when scanning files for Unicode characters (em dashes) and decorative emojis. These are standard text-processing commands used for their intended analytical purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a procedure where the agent ingests and analyzes untrusted external prose and code.
- Ingestion points: Reads target files provided by the user for auditing.
- Boundary markers: None explicitly defined in the skill itself.
- Capability inventory: Uses
grep,perl, andast-grepto process the content. - Sanitization: None. The skill relies on the agent's internal safety filters when processing the external content. This is a low-risk surface inherent to any audit or analysis skill.
Audit Metadata