skills/tanabee/skills/dev/Gen Agent Trust Hub

dev

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a high-level orchestrator for developer workflows. Its behavior, including autonomous execution of implementation steps, aligns with its stated purpose of streamlining GitHub issue resolution.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted content from GitHub issues.
  • Ingestion points: Untrusted data from GitHub issues is ingested through the $ARGUMENTS parameter used in sub-skill calls in SKILL.md.
  • Boundary markers: Absent. No explicit delimiters or instructions to ignore embedded commands are used when passing issue references to other skills.
  • Capability inventory: The skill has access to high-privilege tools including Bash, Write, Edit, and the ability to trigger other skills (/implement, /plan) as defined in SKILL.md.
  • Sanitization: Absent. There is no evidence of input validation or sanitization for the content retrieved from the external issue source.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 11:26 AM