cross-fact-check
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing bash commands such as
catandecho, piping the output to thegeminiCLI tool to perform analysis on local files. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process the content of external documents, creating a surface for indirect prompt injection attacks where malicious instructions embedded in a document could influence the behavior of the Gemini models.
- Ingestion points: Document content is read from the local file system using
cat <ファイルパス>as described in theStep 2section ofSKILL.md. - Boundary markers: The skill does not employ specific delimiters, XML tags, or system-level instructions to encapsulate or isolate the untrusted document content from the fact-checking instructions provided to the CLI.
- Capability inventory: The skill possesses shell execution capabilities (
bash) to read file data and interact with external command-line tools that perform network operations. - Sanitization: There is no evidence of input validation, sanitization, or filtering of the document content before it is passed to the AI models via the CLI.
Audit Metadata