delay-tracker

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection as it processes data from multiple external sources.
  • Ingestion points: The skill reads and interprets data from several project files, including schedule.json, specs-quality.json, daily-report-data.json, cost-data.json, labor-tracking.json, and delay-log.json (as described in the 'Project Intelligence Integration' section of SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions within the prompt to ignore potentially malicious instructions embedded in the project data files.
  • Capability inventory: The skill's capabilities are focused on data analysis, mathematical calculations for project extensions, and generating text-based reports. No high-risk capabilities such as network requests, file-system writes to sensitive paths, or subprocess execution were detected.
  • Sanitization: The instructions do not specify any validation, escaping, or sanitization protocols for the external data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:53 PM
Security Audit — agent-trust-hub — delay-tracker