remove-ai-slop
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
rg(ripgrep) utility to scan the filesystem for relevant source files and instructs the agent to execute the project's own development commands to capture rendered output for visual inspection. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It ingests untrusted data from the target repository, including code comments, markdown files, and copy strings. Malicious instructions embedded within these files could potentially influence the agent's audit findings or the automated remediation steps in Phase 8.
- Ingestion points: Reads all code and content files matching common web extensions (*.tsx, *.md, etc.) across the repository.
- Boundary markers: None explicitly defined to separate audited data from the agent's core instructions.
- Capability inventory: The agent has the ability to read files, write file modifications, and execute shell commands.
- Sanitization: No explicit sanitization or filtering of the repository content is performed before processing.
Audit Metadata