The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Data is ingested from external GitHub issues using the gh issue view command (Step 2, SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted issue content from the agent's core instructions.
Capability inventory: The skill has access to Bash (shell command execution), Write (file system modification), and the Agent tool (delegation of tasks).
Sanitization: The instructions do not specify any sanitization or filtering of the content retrieved from the issue body.
[COMMAND_EXECUTION]: The skill executes shell commands using the Bash tool for repository investigation and issue management.
The skill uses standard utilities including gh (GitHub CLI), git grep, and rg for technical research.
A safety-conscious instruction is included to avoid using grep -r or find, specifically to prevent the agent from accidentally scanning or being blocked by sensitive files listed in .gitignore (such as .secret.local).

research