The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data sources (git logs and phase manifests) to identify commits for reversal. These sources could theoretically contain malicious instructions embedded in commit messages or manifest metadata designed to influence agent behavior during the revert process.
Ingestion points: The skill reads git log output and local phase manifest files to determine which commits to roll back.
Boundary markers: The skill definition does not explicitly define delimiters or specific instructions for the agent to ignore instructions embedded within the git logs or manifests.
Capability inventory: The skill is granted access to the Bash tool, enabling it to execute git revert and other shell commands.
Sanitization: There is no evidence of explicit sanitization or validation logic to filter out prompt injection patterns from the git history or manifest data before processing.

gsd-undo