release-notes

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from potentially untrusted sources, such as existing repository release notes and CHANGELOG files.
  • Ingestion points: Uses gh release view to read existing release bodies and reads the project's local CHANGELOG file (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or "ignore instructions" prompts when processing these files.
  • Capability inventory: The skill has the capability to write to the repository using gh release edit and suggests executing code samples against published artifacts to verify release claims.
  • Sanitization: No specific escaping or validation logic is defined for the content extracted from the changelogs or previous releases.
  • Note: This represents a standard functional surface for a release automation tool and does not indicate malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 05:12 PM