skills/firecrawl/openclaw/gifgrep/Gen Agent Trust Hub

gifgrep

Warn

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs an external binary from a third-party source using Homebrew (steipete/tap/gifgrep) or Go (github.com/steipete/gifgrep/cmd/gifgrep@latest). These sources are outside the verified vendor infrastructure.
  • [COMMAND_EXECUTION]: The skill relies on executing the gifgrep command to search, browse, download, and manipulate GIF files (e.g., gifgrep still, gifgrep sheet).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted metadata such as titles and tags from external GIF providers (Tenor, Giphy). This data enters the agent's context and could potentially influence its behavior.
  • Ingestion points: GIF search results (JSON output or TUI) provided by Tenor and Giphy APIs.
  • Boundary markers: None specified in the instructions to separate external data from system instructions.
  • Capability inventory: Execution of the gifgrep binary, writing files to ~/Downloads, and accessing environment variables for API keys.
  • Sanitization: No explicit sanitization or validation of the content returned from GIF providers is mentioned.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — gifgrep