fp-plan

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides a command to install the fp CLI tool by downloading a script from a remote URL and executing it via shell.
  • Evidence: curl -fsSL https://setup.fp.dev/install.sh | sh -s (SKILL.md)
  • Context: The URL belongs to the vendor's domain and is used for their own tool's setup.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands to manage project structure and interface with external tools.
  • Evidence: Execution of fp issue create, fp tree, gh issue view, and ls commands (SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web sources which could potentially contain embedded instructions.
  • Ingestion points: Fetches issue and document content from GitHub, Linear, and Notion URLs (SKILL.md).
  • Boundary markers: The skill does not define specific markers to delimit external content from internal instructions.
  • Capability inventory: The skill can execute shell commands (fp, gh, ls) and write content to issue management systems (SKILL.md).
  • Sanitization: No explicit sanitization or filtering of the external data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 05:15 PM