The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external GitHub repositories, which presents a surface for indirect prompt injection.
Ingestion points: Processes repository documentation (AGENTS.md, CONTRIBUTING.md) and issue tracker content (comments, issue descriptions) in Step 2.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing this external content.
Capability inventory: The agent has access to Bash(gh:*) and Bash(multica:*) which allow it to post comments and interact with issue trackers.
Sanitization: No explicit sanitization or filtering of the ingested GitHub content is described before the agent performs its analysis or posts its deliverable.
[EXTERNAL_DOWNLOADS]: The skill references an external repository at https://github.com/mmontes11/contributions to verify scoring rubrics during the feasibility evaluation phase.
[COMMAND_EXECUTION]: The skill utilizes command-line interfaces for GitHub operations and project management.
Evidence: Employs gh for repository metadata and issue searching, and multica for posting deliverable comments and updating sub-issue statuses.

contributions-scout