write-a-prd

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh api) to query existing milestone titles and create new milestones within the repository to organize large batches of work.
  • [COMMAND_EXECUTION]: Employs shell commands such as grep to search documentation in docs/solutions/ and ls to locate research artifacts in ~/.claude/research/. These operations are restricted to project-specific local directories.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting data from external sources like GitHub issue bodies and local documentation files. 1. Ingestion points: docs/solutions/ and GitHub issue bodies (Step 4). 2. Boundary markers: Absent; instructions do not specify delimiters or warnings to ignore embedded instructions in ingested data. 3. Capability inventory: Milestone creation (gh api) and repository exploration. 4. Sanitization: Absent.
  • [SAFE]: The identified activities are restricted to the local project environment and the repository's official GitHub API. These functions are intended for legitimate project management and context-gathering tasks within a developer's workflow. No unauthorized data exfiltration or remote code execution patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:58 PM
Security Audit — agent-trust-hub — write-a-prd