The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external issue trackers and incorporates the full, unsanitized issue body into the agent's context. 1. Ingestion points: Data is fetched via the gh CLI, local markdown files, or external tools specified in docs/agents/issue-tracker.md. 2. Boundary markers: While the skill uses markdown headers for structure, it lacks explicit instructions or delimiters to prevent the agent from following commands embedded within issue bodies. 3. Capability inventory: The skill has the ability to execute shell commands and read local files. 4. Sanitization: No filtering or sanitization is applied; the instructions explicitly require the 'complete body' to be presented.
[DYNAMIC_EXECUTION]: The skill executes shell commands that are dynamically retrieved from a local configuration file. Evidence: The instructions for 'Other backends' direct the agent to 'use the method in the Reading section's "List open issues" line' from docs/agents/issue-tracker.md. This allows for arbitrary command execution based on the contents of that file.
[COMMAND_EXECUTION]: The skill relies on executing shell commands, specifically the gh CLI and other dynamically resolved tools, to perform its primary function.

fetch-issues