quality-management

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from multiple untrusted external sources.
  • Ingestion points: The skill reads data from numerous project JSON files, including specs-quality.json, inspection-tracker.json, sub-performance.json, daily-reports.json, plans-spatial.json, directory.json, quality-data.json, and procurement-log.json (referenced in SKILL.md).
  • Boundary markers: No explicit boundary markers or instructions to disregard embedded commands within the ingested data were identified.
  • Capability inventory: The skill performs file read operations and data processing to generate checklists and reports. No high-risk capabilities such as network access, file writing, or subprocess execution were detected in SKILL.md or references/skill-detail.md.
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the external JSON content before it is processed and presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:53 PM
Security Audit — agent-trust-hub — quality-management