The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill contains logic to automatically search for and extract GitHub authentication tokens from local files.
It attempts to read GITHUB_TOKEN from ~/.hermes/.env using grep and cut.
It attempts to extract tokens from ~/.git-credentials using sed if a GitHub entry is present.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issue titles, bodies, and comments, which could contain malicious instructions designed to influence the agent's next actions.
Ingestion points: Data is fetched from https://api.github.com/repos/$OWNER/$REPO/issues and related endpoints in SKILL.md.
Boundary markers: No explicit instructions are provided to the agent to ignore or delimit instructions found within the issue content during processing.
Capability inventory: The skill possesses the ability to execute shell commands (gh, git, curl), write to the filesystem via shell redirects (implied), and perform network operations via curl.
Sanitization: The skill relies on basic Python scripts to parse JSON, but does not perform sanitization of the strings before they are presented to the agent context.

github-issues