qa-verify

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands such as 'npm test', 'npm run build', and 'git diff' to provide objective evidence of task completion and code correctness.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external data from Jira tickets and requirement specifications.
  • Ingestion points: External data enters the agent context through Jira MCP tools and manual specification files as described in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to treat external data as untrusted content, potentially allowing instructions within tickets to influence agent behavior.
  • Capability inventory: The agent is empowered to execute a variety of shell commands and filesystem operations as part of the verification gate process.
  • Sanitization: No sanitization, validation, or escaping of the external content is prescribed before the data is used to inform verification steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 11:29 AM