scan-effect-solutions

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the effect-solutions command-line utility with various subcommands (list, show) to perform the audit tasks. This relies on the tool being present and secure within the agent's environment.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes untrusted data from the repository being audited.
  • Ingestion points: Repository files including tsconfig.json, .ts source files, and documentation in references/.
  • Boundary markers: Absent. The skill does not employ delimiters to separate untrusted code content from its internal processing instructions.
  • Capability inventory: The skill can execute the effect-solutions tool and read arbitrary files from the filesystem.
  • Sanitization: Absent. There is no evidence that the content of the files being audited is sanitized or escaped before being used in the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:26 PM