The Agent Skills Directory

Remote Code Execution (CRITICAL): The skill contains a pattern that pipes a remote script directly to the shell for execution: curl -fsSL https://setup.fp.dev/install.sh | sh -s. This is an extremely dangerous pattern as it allows an unverified third-party server to execute any command on the host system without inspection.
External Downloads (HIGH): The skill relies on an external domain (fp.dev) that is not part of the trusted organizations list. This increases the risk of supply chain attacks or domain hijacking leading to malicious code delivery.
Indirect Prompt Injection (LOW):
Ingestion points: The skill ingests untrusted data from issue descriptions, comments, and project trees using commands like fp context, fp log, and fp tree.
Boundary markers: There are no boundary markers or instructions to ignore embedded commands within the issue data being processed.
Capability inventory: The agent has the ability to execute CLI commands, modify issue statuses, and potentially commit changes to a version control system.
Sanitization: The skill lacks any visible sanitization or validation of the data retrieved from external issue trackers before processing it.

fp-implement