anp-agent

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill dynamically fetches Agent Description (AD) documents and interface schemas from remote URLs (e.g., agent-connect.ai, agent-search.ai) or user-provided endpoints to determine RPC methods and server locations.
  • [COMMAND_EXECUTION]: The setup.sh script executes shell commands to install dependencies (anp, aiohttp) and utilizes openssl to generate local secp256k1 cryptographic keys used for identity verification.
  • [CREDENTIALS_UNSAFE]: The skill generates and manages a local private key (config/private-key.pem) and a DID document (config/did.json). These sensitive files are used to sign requests sent across the ANP network.
  • [DATA_EXFILTRATION]: The call_method function in scripts/anp_cli.py performs network operations to non-whitelisted RPC endpoints. These requests include user-provided parameters and cryptographic signatures, potentially exposing user interaction data to third-party agents.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external sources.
  • Ingestion points: scripts/anp_cli.py (fetches remote JSON configuration and receives RPC responses from external agents via the anp library).
  • Boundary markers: Absent. Data returned from external agents is printed directly to the terminal and returned to the agent context without delimiters or warnings.
  • Capability inventory: scripts/anp_cli.py (has the ability to perform network requests and access local configuration files).
  • Sanitization: None. External content is parsed as JSON but not sanitized for malicious instructions before being presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 09:03 PM