Skills
skills/longbridge/skills/longbridge-basicinfo/Gen Agent Trust Hub

longbridge-basicinfo

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the longbridge CLI tool (specifically the static, company, and calc-index subcommands) with user-provided parameters.- [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it incorporates untrusted user data into command-line arguments.
  • Ingestion points: The <SYMBOL> parameter used in the CLI execution instructions in SKILL.md.
  • Boundary markers: Absent; the instructions do not specify delimiters or escaping mechanisms to isolate the symbol input from the rest of the shell command.
  • Capability inventory: Shell command execution via the longbridge binary.
  • Sanitization: Absent; the skill relies on the agent following the provided symbol format table rather than implementing explicit sanitization or validation of the input string.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 04:42 AM