The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from multiple external sources.
Ingestion points: GitHub Pull Requests (via gh pr view and gh pr diff), git commit logs, changelogs, and local markdown files as specified in SKILL.md.
Capability inventory: The skill has the ability to execute shell commands (git, gh) and write generated content to the local filesystem (emails/<slug>.md).
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings for the external data being processed.
Sanitization: The skill lacks explicit sanitization steps for content fetched from PRs or git logs before it is interpolated into the generation prompt.
[COMMAND_EXECUTION]: The skill invokes external CLI tools including git and gh to retrieve content for analysis. While standard for development workflows, this interaction constitutes a vector for ingesting external data.

newsletter