The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the GitHub CLI (gh) to perform repository management tasks. It executes commands such as gh issue list, gh issue create, gh issue edit, and gh api to synchronize the state of the local PRD with the remote GitHub repository.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests data from external PRD files and incorporates it into automated workflows.
Ingestion points: The skill reads content from PRD markdown files (e.g., docs/PRD.md or tasks/prd-[feature].md) as specified in the Workflow section of SKILL.md.
Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious embedded prompts within the PRD content.
Capability inventory: The agent has the capability to execute shell commands via the GitHub CLI (gh), which includes creating issues, editing repository metadata, and making arbitrary API calls via gh api as documented in SKILL.md.
Sanitization: There is no evidence of input validation, escaping, or sanitization of the text extracted from the PRD before it is passed as arguments (e.g., --title or --body) to the gh tool.

prd-to-github-milestone