The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data in the form of work requests from users.
Ingestion points: Untrusted data enters the agent context through the "REQUEST RECEIVED" step described in SKILL.md.
Boundary markers: The skill does not employ explicit boundary markers or delimiters for the ingested request data.
Capability inventory: The skill uses the gh CLI (GitHub) for reading project information and the mcp__memory__create_entities tool to store intake assessments.
Sanitization: There is no evidence of input sanitization or validation of the request content before it is stored in memory or used for scoping decisions.
[COMMAND_EXECUTION]: The skill provides bash scripts intended for environment verification. These scripts use the GitHub CLI (gh) to check the status of project boards and verify that required environment variables such as GITHUB_PROJECT_NUM and GH_PROJECT_OWNER are correctly set.

work-intake