qa-task-creator

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources to generate GitHub issues and documentation.
  • Ingestion points: The skill reads data from various sources including "Coverage gaps", "Spec-auditor findings", "Risk-analyzer output", and "Bug reports" as defined in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters mentioned to isolate these external inputs from the skill's own instructions, which may allow embedded malicious prompts in a bug report to influence the output format or content.
  • Capability inventory: The skill has the capability to perform network-based operations via the GitHub MCP, specifically searching for and creating GitHub Issues (SKILL.md).
  • Sanitization: The skill lacks explicit sanitization or validation steps for the content ingested from external bug reports or coverage tools before it is used to populate task templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-task-creator