changeset
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from pull request bodies, commit messages, and code diffs to generate release documentation, creating a potential surface for instructions embedded in those sources to influence agent behavior. \n
- Ingestion points: PR descriptions, branch diffs, and existing changeset files are processed as outlined in SKILL.md and references/registry.md. \n
- Boundary markers: The instructions do not define explicit delimiters or warnings to separate untrusted external content from the skill's instructions. \n
- Capability inventory: The skill is capable of writing files to the repository (.changeset/ and apps/www/src/registry/changelog/) and executing local maintenance scripts. \n
- Sanitization: No sanitization or validation of the external text content is mentioned before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts to manage and verify registry changelogs. \n
- Evidence: The references/registry.md file specifies commands such as
node tooling/scripts/generate-ui-changelog-entries.mjsandbun test tooling/scripts/generate-ui-changelog-entries.test.mjs. These are vendor-provided local tools for repository maintenance.
Audit Metadata