skills/juliusbrussee/skills/fuck-slop/Gen Agent Trust Hub

fuck-slop

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides specific shell commands (grep, tr, sed, awk) as examples for mechanically scanning drafts for stylistic tells and sentence length consistency. These commands use standard Unix utilities and are intended for local text analysis.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted user-provided text for stylistic refinement, which creates an indirect prompt injection surface.
  • Ingestion points: User-supplied drafts provided via the fuck-slop command or keyword triggers (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the external text.
  • Capability inventory: The skill uses shell-based text analysis tools (grep, etc.) and performs iterative rewrites based on patterns in the input (SKILL.md, references/tells.md).
  • Sanitization: No explicit sanitization or filtering of the input text is performed prior to the analysis pass.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:55 PM
Security Audit — agent-trust-hub — fuck-slop