skills/archibate/agent-skills/jina-ai/Gen Agent Trust Hub

jina-ai

Fail

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: HIGHDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The scripts/dedup_images.py script included in the skill contains logic that reads arbitrary local files and transmits their contents to an external server.
  • Evidence: The to_image function in scripts/dedup_images.py accepts a path as an argument and uses Path.read_bytes() to read the entire file if it exists locally.
  • Evidence: The binary content is then base64-encoded and sent via a POST request to https://api.jina.ai/v1/embeddings.
  • The script lacks file-type validation, meaning it could be coerced into reading and exfiltrating sensitive files (e.g., SSH keys, environment variables) if they are passed as arguments instead of images.
  • [COMMAND_EXECUTION]: The skill's instructions recommend the use of shell pipes and xargs for parallel processing of queries, which can introduce command injection risks if inputs are maliciously crafted.
  • Evidence: Examples such as jina expand "LLM" | xargs -P 5 -I {} jina search "{}" rely on the shell's expansion behavior and could be manipulated by unexpected output from subcommands.
  • [EXTERNAL_DOWNLOADS]: The skill installs external software and fetches academic data from well-known public sources.
  • The skill installs the jina-cli tool using the uv tool manager.
  • It fetches PDF files and research papers from arxiv.org and search results from ssrn.com.
  • [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by ingesting and processing data from untrusted external sources.
  • Ingestion points: Web page content extracted via jina read, search snippets from jina search, and academic paper text from PDF extractions.
  • Boundary markers: The instructions do not specify the use of delimiters or isolation protocols when the agent processes the ingested data.
  • Capability inventory: The agent has access to local file system reading (via scripts/dedup_images.py), network transmission capabilities, and shell command execution.
  • Sanitization: No explicit content sanitization or filtering logic is provided for handling untrusted external data.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 10, 2026, 06:46 AM