docs-cleaner

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by reading and analyzing untrusted documentation files.
  • Ingestion points: Documentation files in Markdown (.md) or MDX (.mdx) format are processed by the scripts/docs_inventory.sh script and subsequently analyzed by the agent.
  • Boundary markers: The skill lacks explicit boundary markers or instructions used to ensure the agent ignores potentially malicious commands embedded within the documents being analyzed.
  • Capability inventory: The skill workflow includes the capability to create, modify, and delete files (e.g., replacing files with stubs) based on the content analysis.
  • Sanitization: While basic heading sanitization is performed for the inventory table in the helper script, there is no logic to sanitize or validate the full text of documents before the agent processes them.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 11:05 AM