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

gifgrep

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the gifgrep utility via Homebrew (steipete/tap/gifgrep) or Go (github.com/steipete/gifgrep/cmd/gifgrep@latest).
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands using the gifgrep binary to interact with GIF providers, download files to the local filesystem, and generate image assets like stills and contact sheets.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data from third-party GIF providers (Tenor and Giphy).
  • Ingestion points: Search results, titles, and metadata returned from provider APIs.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: The skill allows file writing (-o), downloads to ~/Downloads, and binary execution via the CLI.
  • Sanitization: The skill advises manual verification of asset headers and content-types, though it does not provide automated sanitization of metadata strings that could influence agent logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:39 AM