skills/polya20/grill-me/writing-shape/Gen Agent Trust Hub

writing-shape

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process untrusted markdown data (the 'pile') which could potentially contain indirect instructions. While this creates a theoretical surface for indirect prompt injection, the risk is negligible given the skill's limited scope and the absence of high-privilege capabilities.
  • Ingestion points: Reads user-provided markdown files from the local filesystem to serve as source material (SKILL.md).
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or ignore embedded instructions within the source material.
  • Capability inventory: Local file system read and append access (SKILL.md).
  • Sanitization: Absent; the input is treated as natural language fragments to be restructured into a new document.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:36 AM
Security Audit — agent-trust-hub — writing-shape