workflow-release-prep

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection where untrusted data could influence agent behavior.
  • Ingestion points: The user's prompt is passed directly as context to the /workflow-start command in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to treat the interpolated user prompt as data rather than instructions.
  • Capability inventory: The skill orchestrates a sequence of high-level actions including /sre-review, /quality-gate, and /status as defined in SKILL.md.
  • Sanitization: No validation, escaping, or filtering of the user prompt is performed before interpolation into the workflow command.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 03:49 AM