source-tutorial-spec

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for the agent to process local data files (sources/index.jsonl, sources/provenance.jsonl, GOAL.md, DECISIONS.md) and generate a markdown-formatted tutorial specification (output/TUTORIAL_SPEC.md).
  • Capability assessment: The skill does not request network access, execute shell commands, install third-party packages, or access sensitive system directories.
  • Data handling: While the skill processes potentially untrusted source data (Indirect Prompt Injection surface), its impact is limited to the generation of a documentation file, and it lacks the dangerous capabilities (network, execution) required for an injection to be effectively exploited.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:47 AM