The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data which may contain hidden instructions designed to influence the agent.
Ingestion points: The skill reads pull request diffs using git diff and fetches issue references or spec files using the gh tool, as described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between code/data and potential instructions within the ingested content.
Capability inventory: The skill uses git and gh via Bash to retrieve repository state and issue details.
Sanitization: The instructions do not specify any validation or sanitization steps for the content retrieved from the diffs or issue tracking system.

code-review