The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process code containing merge conflicts, which serves as an untrusted data source that could contain malicious instructions.
Ingestion points: The workflow in SKILL.md identifies conflicting files via git status and conflict markers for processing.
Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from inadvertently following instructions that might be embedded within the source code or conflict markers.
Capability inventory: The skill triggers the execution of local package managers, compilers, and test suites (Workflow steps 4 and 5), creating an execution surface for potentially malicious code during the validation phase.
Sanitization: There is no mention of sanitizing or filtering the content of the conflicts before the agent processes them or executes tests on the resolved state.

fix-merge-conflicts