The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or unauthorized data access were detected. The skill provides a legitimate interface for managing app-related recovery tasks.
[COMMAND_EXECUTION]: The skill executes the gpc command-line utility. These executions are limited to specific subcommands like recovery and vitals, aligning with the utility's intended administrative use case.
[PROMPT_INJECTION]: The skill processes external JSON files, which serves as a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Files recovery.json and targeting.json are passed as arguments to the gpc recovery create and gpc recovery add-targeting commands.
Boundary markers: None identified; the tool relies on file path inputs.
Capability inventory: Executes gpc for listing, creating, deploying, and cancelling recovery actions, as well as checking crash vitals.
Sanitization: Not applicable as the agent handles file paths rather than interpreting file contents directly within its own prompt logic.

gpc-app-recovery