The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses bunx to fetch the algal-skills package from the public npm registry at runtime.
[REMOTE_CODE_EXECUTION]: The skill executes code from the downloaded algal-skills package via bunx using the exec tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from GitHub CI run metadata (status, title, etc.), which could serve as a vector for indirect prompt injection if the output is subsequently processed by an AI agent.
Ingestion points: Data is retrieved from GitHub via the gh run list command as described in the skill logic in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the skill instructions.
Capability inventory: The skill utilizes the exec tool to run commands and poll for status updates.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the GitHub API before it is processed or returned.

algal-ci