fabric
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill clones the Fabric repository from 'https://github.com/danielmiessler/fabric.git' to manage patterns. It also includes instructions for updating the repository via 'git pull'.
- [COMMAND_EXECUTION]: The skill relies on shell command execution for its core functionality. The agent executes 'git clone', 'git pull', 'cd', and 'ls' for repository management, and the 'fabric' CLI to process content.
- [DATA_EXFILTRATION]: The skill performs network operations via the 'fabric' CLI to fetch content from external URLs and YouTube videos for analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a processing engine for untrusted external data, creating a potential vector for indirect prompt injection.
- Ingestion points: Content is ingested via remote URLs, YouTube links, local files, and direct user input.
- Boundary markers: No explicit boundary markers or instructions are used to separate untrusted content from the system instructions or to warn the agent to ignore instructions within the data.
- Capability inventory: The agent can execute shell commands, perform network requests (via 'fabric'), and manage a local repository.
- Sanitization: There is no evidence of sanitization or filtering of the content before it is processed by the Fabric patterns.
Audit Metadata