functional-release-notes

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git cherry -v and git diff-tree to resolve commits and identify file changes. These are standard development operations for generating release notes and do not involve untrusted shell interpolation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Notion workspaces, Slack history, and GitHub PR/issue context to identify requestors and trace feature origins.
  • Ingestion points: Data enters the context via the git command outputs, GitHub API data, Slack history searches, and Notion page reads (SKILL.md, steps 8-9).
  • Boundary markers: The instructions do not define specific boundary markers for external data, but they do require the output to be synthesized into business-oriented narratives and specific formats, which naturally constrains the influence of raw external text.
  • Capability inventory: The skill has read-only access to repository history, Slack, and Notion. It does not perform file-write or network-post operations.
  • Sanitization: There is no explicit sanitization step described for the external content before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 04:24 PM
Security Audit — agent-trust-hub — functional-release-notes