skills/hirokisakabe/pkm-kit/page-edit/Gen Agent Trust Hub

page-edit

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from a local markdown repository, which constitutes an ingestion surface for untrusted content if the repository contains files from external sources.
  • Ingestion points: Local markdown files read during deduplication and freshness checks (SKILL.md).
  • Boundary markers: None specified for the processed file content.
  • Capability inventory: Uses shell-based search tools (grep, rg) and file modification tools (Edit, str_replace, apply_patch) as described in the instructions.
  • Sanitization: No explicit sanitization or validation of the file content is performed before processing.
  • [EXTERNAL_DOWNLOADS]: References official documentation and specification repositories on GitHub (e.g., github.com/anthropics/skills), which are established and safe resources.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 10:47 AM
Security Audit — agent-trust-hub — page-edit