skills/hughyau/qiushi-skill/mass-line/Gen Agent Trust Hub

mass-line

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or unauthorized data access techniques were detected. The skill provides philosophical and methodological instructions for information gathering and synthesis.
  • [DATA_EXPOSURE]: The skill mentions accessing git history, logs, and test results as information sources. This is consistent with the intended purpose of a development-oriented AI agent and does not involve hardcoded credentials or unauthorized exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing external, potentially untrusted feedback data.
  • Ingestion points: Processes feedback from users and stakeholders via the feedback-synthesizer-prompt.md agent.
  • Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are provided for the input feedback.
  • Capability inventory: No executable capabilities (subprocess, eval, file-write) are present in the provided skill files; the skill is purely instructional/prompt-based.
  • Sanitization: No sanitization or validation of the input feedback is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 03:41 AM