Caveat verdict
agentic-doc-parse-and-extract
Official CLI tool from Laiye Technology for document parsing and extraction that reads an API key via config, sends documents to an ADP service for processing, and returns structured data — all behavior matches the stated enterprise document-processing purpose with no hidden destinations or suspicious capabilities.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (3)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
references/examples.md · code · curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-i
Pipe to bash — executes piped content as shell commands
references/examples.md · code · | bash
Base64 encoding/decoding
references/commands.md · prose · downgraded · base64-encode
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encoding Is this flag fair?
Thanks — recorded.