sprint-planner

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • No Code (SAFE): The skill consists exclusively of Markdown documentation and YAML templates. There are no scripts, binaries, or installation procedures that could execute malicious logic on a host system.
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and process external plans to generate sprint definitions, which introduces an indirect injection surface.
  • Ingestion points: The workflow in SKILL.md reads untrusted plan data from the $ARGUMENTS variable or user descriptions.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard instructions embedded within the ingested plan data.
  • Capability inventory: While the planner skill itself only generates text, the workflow it defines for the agent includes high-privilege capabilities such as running build commands, git operations, and potentially making network requests (as seen in the example success metrics).
  • Sanitization: There is no mechanism within the skill to sanitize or validate the content of the plan before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 05:03 AM