The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (GitHub issues) which could be used to manipulate the agent's behavior.
Ingestion points: The skill fetches issue titles, bodies, and comments using gh issue list and gh issue view as described in SKILL.md.
Boundary markers: The skill lacks explicit delimiters or instructions to treat issue content as data rather than instructions, which could allow an attacker to embed malicious commands within an issue.
Capability inventory: The skill has access to powerful tools including Bash, Write, and Edit, enabling it to modify the codebase, run tests, and push changes to a repository via git and gh CLI.
Sanitization: There is no mention of sanitization, filtering, or validation of the fetched issue content before it is used by the model to implement fixes.

gh-issues