launchdarkly-flag-cleanup

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill requires the @launchdarkly/mcp-server package as specified in marketplace.json. Because the author organization is not in the predefined trusted sources list, this is flagged as an unverifiable external dependency.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data by scanning the local codebase (SKILL.md Step 1). Evidence: 1. Ingestion points: codebase file contents; 2. Boundary markers: absent; 3. Capability inventory: file read, file write, and network access via MCP; 4. Sanitization: none.
  • COMMAND_EXECUTION (LOW): The verification workflow in SKILL.md (Step 6) directs the agent to execute build and lint commands, which runs locally defined and potentially untrusted scripts within the target project.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:05 PM