skills/ericrisco/rsc-harness/clarify/Gen Agent Trust Hub

clarify

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates on local project documentation within the 02-DOCS directory. It focuses on text analysis and modification without invoking external scripts, network resources, or administrative shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from specification files for analysis and updates.
  • Ingestion points: Reads project specification files in 02-DOCS/wiki/sdd/specs/.
  • Boundary markers: None present to distinguish spec content from instructions.
  • Capability inventory: Limited to reading and writing local documentation files.
  • Sanitization: Not applicable as the output is intended to be markdown text within the same documentation context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 11:10 PM
Security Audit — agent-trust-hub — clarify