skill-comply
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted markdown files (skills or rules) as input to generate behavioral specs and test scenarios. Maliciously crafted input files could potentially influence the LLM to generate harmful setup commands or adversarial prompts during the scenario generation phase.\n
- Ingestion points:
scripts/run.pyreads the target skill file provided in the command line argument.\n - Boundary markers: The prompt templates in
prompts/scenario_generator.mdandprompts/spec_generator.mduse---delimiters to wrap external skill content but do not include explicit instructions for the LLM to ignore or treat instructions within that content as data only.\n - Capability inventory:
scripts/runner.pyusessubprocess.runto execute generatedsetup_commandsand invokes theclaudeCLI with generated prompts.\n - Sanitization: The tool uses
shlex.splitto parse generated commands and includes logic in_safe_sandbox_dirto prevent directory traversal outside of the intended sandbox base path.\n- [COMMAND_EXECUTION]:scripts/runner.pyexecutes shell commands (setup_commands) that are produced by the LLM during scenario generation. While these are executed within a restricted sandbox, the commands themselves are derived from analysis of untrusted input files.\n- [DYNAMIC_EXECUTION]: The tool dynamically constructs and executes behavioral tests and environment setup steps at runtime based on the interpretation of provided skill files.
Audit Metadata