to-prd
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources to generate documentation.
- Ingestion points: Ingests content from Linear project briefs, Notion page discussions (via
include_discussions: true), and local artifacts like./docs/approach.mdand./ideas/reports/*-ideate.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its own instructions and content found in external sources.
- Capability inventory: The skill performs file writes to the local system, executes shell commands (
gh issue create), and interacts with the Notion and Linear APIs. - Sanitization: The instructions do not specify any validation or sanitization requirements for data retrieved from external platforms before it is interpolated into the generation prompts.
- [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through the GitHub CLI.
- Evidence: The skill instructs the agent to run
gh issue create --title "[PRD] <Feature Name>" --body-file ./docs/prd-<feature>.mdto publish documentation as GitHub issues. While the instructions recommend kebab-casing the feature name for filenames, the title interpolation remains a potential surface for command injection if the feature name is maliciously crafted.
Audit Metadata