skills/myuon/harness/sync/Gen Agent Trust Hub

sync

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes npx skills ls --json and npx skills ls -g --json to retrieve the current list of skills. These commands use the well-known npx utility to run package binaries.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing descriptions from local SKILL.md files to infer installation conditions. * Ingestion points: Reads description text from SKILL.md files of other skills in Step 4. * Boundary markers: None identified in the processing logic. * Capability inventory: Ability to update the ~/.config/harness/manifest.json file in Step 6. * Sanitization: No explicit sanitization of the description content is mentioned.
  • [SAFE]: The access and modification of the ~/.config/harness/manifest.json file are essential to the skill's purpose and do not constitute unauthorized persistence or data exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 05:22 AM
Security Audit — agent-trust-hub — sync