skills/eins78/skills/plot-sprint/Gen Agent Trust Hub

plot-sprint

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Git commands (git add, git commit, git push, git rm) to manage files within the docs/sprints/ and docs/plans/ directories. This is the primary function of the skill, facilitating a workflow where sprint coordination artifacts are committed directly to the main branch.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by reading and parsing untrusted data from local repository files.
  • Ingestion points: Reads sprint definitions, goals, and task lists from docs/sprints/*.md and docs/plans/active/*.md.
  • Boundary markers: None identified; the skill parses Markdown checkbox states and HTML comment annotations (e.g., <!-- pr: #N ... -->) directly from the files.
  • Capability inventory: Limited to directory creation (mkdir), symbolic link management (ln -s), and Git operations within the project scope.
  • Sanitization: The skill validates the format of the sprint slug (lowercase, hyphens) but does not sanitize the text of sprint goals or task descriptions before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 03:02 AM