Skills
Navigate
skills/kdy1/kdy1-scripts/write-prd/Gen Agent Trust Hub

write-prd

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from target repositories, creating a surface for indirect prompt injection.
  • Ingestion points: SKILL.md Workflow Step 1 instructs the agent to read docs, contracts, issue templates, and code.
  • Boundary markers: Absent; the instructions do not explicitly separate external data or warn the agent to ignore embedded instructions.
  • Capability inventory: SKILL.md Workflow Step 5 and 'Useful Commands' use the gh CLI to create issues.
  • Sanitization: Absent; there is no specified validation or filtering of the repository data before it informs the agent's actions.
  • [COMMAND_EXECUTION]: The skill executes shell commands via the gh CLI. It mitigates shell injection risks by instructing the agent to use quoted variables and paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 10:21 AM