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

gifgrep

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and metadata direct the installation of the gifgrep CLI tool from the author's GitHub repository (github.com/steipete/gifgrep) and Homebrew tap (steipete/tap/gifgrep).
  • [COMMAND_EXECUTION]: The skill uses the gifgrep command-line tool to perform searches, download files, and extract images from GIF files.
  • [CREDENTIALS_UNSAFE]: The documentation mentions the use of API keys (GIPHY_API_KEY, TENOR_API_KEY) for accessing GIF providers; however, no hardcoded secrets are present in the skill files.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external GIF provider APIs, representing a surface for indirect prompt injection. 1. Ingestion points: API responses from Tenor and Giphy via gifgrep search. 2. Boundary markers: Absent; no delimiters are defined when processing external metadata. 3. Capability inventory: Includes shell command execution (gifgrep), file downloads to ~/Downloads, and image processing (stills/sheets). 4. Sanitization: No explicit sanitization or validation of external API content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 02:11 PM
Security Audit — agent-trust-hub — gifgrep