easykol

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill routinely installs and updates its core CLI tool, @easykol/cli, from the official npm registry and uses npx to update skill configurations.\n- [COMMAND_EXECUTION]: The skill executes multiple CLI commands (such as easykol search, kol, audience, and emails) to interact with the EasyKOL platform. These operations are within the scope of the skill's primary purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests natural-language descriptions from the user and interpolates them into the --sentence parameter for search commands, creating a potential injection surface.\n
  • Ingestion points: User-provided search strings are ingested in SKILL.md.\n
  • Boundary markers: No explicit boundary markers or instruction-ignoring wrappers are used for the user input.\n
  • Capability inventory: The skill can execute CLI commands, perform network requests to app.easykol.com, and read/write configurations in the user's home directory.\n
  • Sanitization: The skill relies on the EasyKOL CLI's internal handling of the sentence parameter to prevent malicious interpretation of the input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 02:12 PM
Security Audit — agent-trust-hub — easykol