skills/promptdriven/pdd/pdd-prompting/Gen Agent Trust Hub

pdd-prompting

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's core workflow requires the agent to read and follow instructions contained in .prompt.md and user_stories/*.md files within the repository. This creates a surface for indirect prompt injection if an attacker can commit malicious content to these files.
  • Ingestion points: The agent is instructed to ingest data from files such as prompts/*.prompt.md, user_stories/*.md, and tests/*.json as described in SKILL.md, RUNBOOK.md, and guide.md.
  • Boundary markers: The skill documentation mentions the use of pdd-boundary blocks to narrow scope (referenced in runbook/files-and-runtime-block.md).
  • Capability inventory: The agent has the capability to execute shell commands (pdd, gh), read and write to the filesystem, and interact with GitHub Pull Requests.
  • Sanitization: The workflow includes mandatory human approval gates (using pdd approve --said) before code changes or merges can proceed, acting as a defense against unintended instruction following.
  • [COMMAND_EXECUTION]: The skill relies on the execution of local command-line tools to perform its functions.
  • Evidence: Instructions in SKILL.md, RUNBOOK.md, and other runbook files direct the agent to use pdd test, pdd lint, pdd simulate, gh pr merge, and other CLI-based tools to verify behavior and manage the development process. The skill explicitly warns against shell-interpolating untrusted words when commenting on PRs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 03:21 AM