release-notes-drafter

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of high-level natural language instructions. No malicious patterns, such as prompt injection or data exfiltration, were detected within the text.
  • [NO_CODE]: There are no Python scripts, Node.js files, shell commands, or other executable components associated with this skill.
  • [PROMPT_INJECTION]:
  • Ingestion points: The skill accepts external text data such as pull request descriptions and commit messages (SKILL.md).
  • Boundary markers: None specified.
  • Capability inventory: None. The skill does not have access to the file system, network, or shell execution.
  • Sanitization: None specified.
  • Note: While the skill processes untrusted text, it lacks any capabilities that could be exploited by indirect prompt injection. The output is a draft for human review.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 03:40 PM