content-de-slop-ai

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process AI-assisted drafts provided by users, which constitutes an ingestion point for untrusted data that could contain malicious instructions.
  • Ingestion points: The skill ingests external text drafts as primary input for the 'de-sloping' process, as referenced in SKILL.md.
  • Boundary markers: The instructions do not implement boundary markers or delimiters to separate the ingested draft from the skill's operational instructions.
  • Capability inventory: The skill relies on the agent's core text transformation and generation capabilities to execute the multi-step rewrite process described in references/tell-inventory.md and references/detection-tests.md.
  • Sanitization: There are no instructions for sanitizing or filtering the input content to prevent instructions within the draft from being executed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:46 AM
Security Audit — agent-trust-hub — content-de-slop-ai