protocolsio-integration
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the protocols.io API (protocols, steps, comments) which may contain instructions intended to influence the agent's behavior.
- Ingestion points:
scripts/protocols_read.pyperforms GET requests to fetch JSON protocol data and PDF files. - Boundary markers:
SKILL.mdcontains an explicit Operating Contract (Rule #7) instructing the agent to treat remote content as untrusted data and never obey embedded instructions. - Capability inventory: The skill has the capability to write private files to the local directory (0600 permissions) and execute bundled Python scripts.
- Sanitization: The
sanitize_untrustedfunction inscripts/_common.pyredacts keys associated with credentials and truncates long strings to prevent context stuffing or injection. - [COMMAND_EXECUTION]: The skill relies on bundled Python scripts to perform its operations.
- Evidence: The skill instructions direct the agent to execute
scripts/protocols_read.py,scripts/plan_write_request.py, andscripts/validate_protocol_json.pyusingpython3 -B. - Mitigations: All scripts are limited to the Python standard library. The scripts implement strict path validation (
_path_inside_cwd) to ensure file operations are restricted to the current working directory and prevent traversal attacks. - [DATA_EXFILTRATION]: The skill implements strong network egress controls to prevent the exfiltration of sensitive local data.
- Evidence:
scripts/_common.pyimplements a hostname allowlist that restricts HTTPS requests toprotocols.ioand its legitimate subdomains. - Mitigations: The skill uses a custom
NoRedirectHandlerto prevent the leakage of bearer tokens across origins during HTTP redirects. It explicitly avoids loading.envfiles or inspecting the full environment, targeting only the namedPROTOCOLS_IO_ACCESS_TOKENvariable.
Audit Metadata