cycle-time-analyzer

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by ingesting and processing untrusted data from issue trackers.
  • Ingestion points: Untrusted data enters the agent context through scripts/flow_metrics.py which reads issue IDs, titles, and types from a JSON file provided via the --input flag.
  • Boundary markers: The generated reports in Markdown, Notion, or Confluence formats do not utilize specific delimiters or "ignore instructions" warnings to isolate user-provided data from the tool's output.
  • Capability inventory: The script performs file read operations and mathematical computations. It can write output to stdout or a file. It does not have network access or dynamic code execution capabilities.
  • Sanitization: The script performs no escaping or sanitization of issue titles or types before interpolating them into the final output reports, meaning any malicious instructions embedded in the source data will be presented directly to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 03:19 AM