agile-coach

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates entirely locally using provided Python scripts and reference documents. Detailed code review of agile_maturity_scorer.py, team_health_checker.py, and velocity_analyzer.py confirms they are limited to data processing and reporting; they do not perform network operations, access sensitive system files (like SSH keys), or execute arbitrary commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied JSON data which is then interpreted by the agent, creating a potential surface for indirect prompt injection. However, the risk is minimal because the associated scripts lack the capabilities necessary for exploitation.
  • Ingestion points: Untrusted data enters the context via JSON file inputs (assessment, survey, and sprint data) provided as arguments to the scripts in the scripts/ directory.
  • Boundary markers: The script outputs do not use specific delimiters or instructions to isolate the data from the agent's system prompt.
  • Capability inventory: No high-risk capabilities are present in the skill; there are no network operations, file system writes, or subprocess calls in any script.
  • Sanitization: The scripts use standard JSON parsing with no additional sanitization of string content before it is printed to the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 03:19 AM