The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from pull request titles, bodies, and discussion threads (Step 2). Without explicit boundary markers or sanitization, malicious instructions embedded in these fields could influence agent behavior during the revival process.\n- [COMMAND_EXECUTION]: The skill performs shell-level operations including git rebase/push (Steps 7, 10) and executes 'focused checks' (Step 9). Since these checks typically involve running test scripts or build tools defined within the repository being processed, it creates a surface for executing code provided by a potentially untrusted PR author.

ds-revive