skills/paulrberg/dot-agents/md-docs/Gen Agent Trust Hub

md-docs

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Utilizes standard system utilities (git, ls, cat, cp, ln, diff, fd, find, grep, jq) to analyze project structures, extract metadata from configuration files, and manage the documentation lifecycle.\n- [EXTERNAL_DOWNLOADS]: Employs curl -sI to verify the accessibility of external links found within the CONTRIBUTING.md file by performing HTTP HEAD requests during the update workflow.\n- [PROMPT_INJECTION]: Presents a surface for indirect prompt injection as it interprets data from untrusted project files to drive documentation generation.\n
  • Ingestion points: Reads contents from files such as README.md, package.json, and CONTRIBUTING.md to gather context.\n
  • Boundary markers: Does not implement explicit delimiters or guardrail instructions to distinguish project data from agent instructions during processing.\n
  • Capability inventory: Possesses the ability to read and write files in the local repository.\n
  • Sanitization: No formal sanitization or filtering is applied to the content extracted from the project files before generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:32 AM