local-llm-bridge
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from project files and task instructions to be processed by a sub-agent. \n
- Ingestion points: The skill reads
INPUT_FILEcontents and processes arbitrary<INSTRUCTION>strings via therun_agent.pyscript. \n - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are documented in the orchestration patterns. \n
- Capability inventory: The agent has access to
Bash,Read, andWritetools, providing a surface for misuse if the LLM follows malicious instructions within the data. \n - Sanitization: The documentation does not describe any sanitization or validation of the input data before it is passed to the LLM. \n- [COMMAND_EXECUTION]: The skill relies on executing local Python scripts (
run_agent.py,run_server.py) via theBashtool to orchestrate model interactions and manage the local server state.
Audit Metadata