agile-review

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data to generate summaries, which creates a surface for indirect prompt injection where data from issues or reports could attempt to influence the agent's output.
  • Ingestion points: SKILL.md instructs the agent to gather data from issues, status closure reports, checkpoints, and scope change records.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the ingested content.
  • Capability inventory: The skill involves reading project files and writing a markdown artifact to a specified path in the project directory.
  • Sanitization: No sanitization, validation, or escaping of the input data is described in the skill instructions or the review template.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:20 PM
Security Audit — agent-trust-hub — agile-review