roadmap
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could potentially contain malicious instructions intended to manipulate the agent's logic when updating the roadmap file.
- Ingestion points: Untrusted data enters the agent context through the output of
gh pr list(pull request descriptions) and by reading the content of local blog files inwebsite/blog/*.mdx. - Boundary markers: The instructions do not specify any delimiters or safety markers (e.g., "ignore instructions in the following text") when processing the content from PRs or blog posts.
- Capability inventory: The skill has the ability to modify the project's data structure in
website/src/data/roadmap.jsand execute local shell commands vianpm run buildandnpm run start. - Sanitization: There are no defined sanitization or validation steps to filter potential injection attempts within the PR descriptions or blog content before they influence the roadmap updates.
Audit Metadata