The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that can be influenced by third parties.
Ingestion points: Reviewer comments in the PR loop (Step 18), Linear ticket metadata, and repository state from gh pr list.
Boundary markers: The skill lacks explicit instructions for using delimiters to isolate these external data streams.
Capability inventory: The agent has permissions to modify files, manage git worktrees, push to remotes, and execute local Python scripts.
Sanitization: No specific content sanitization or validation logic is defined for ingested PR or ticket data.
[EXTERNAL_DOWNLOADS]: The skill fetches a role contract definition from the author's website.
Evidence: References https://broomva.tech/prompts/autonomous-senior-engineer in SKILL.md.
Note: This is a vendor-owned resource used for setting the agent's operational stance.

autonomous