gifgrep

Warn

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's metadata specifies the installation of the 'gifgrep' binary from external sources, specifically using a Homebrew tap ('steipete/tap/gifgrep') and a Go module ('github.com/steipete/gifgrep/cmd/gifgrep@latest').
  • [COMMAND_EXECUTION]: The skill uses the 'gifgrep' command to perform various operations including searching, downloading files to the '~/Downloads' directory, and interacting with the system's file manager using the '--reveal' flag.
  • [PROMPT_INJECTION]: The skill processes untrusted metadata (titles, tags, and JSON results) from external GIF providers (Tenor and Giphy). This ingestion of external content into the agent context creates a surface for indirect prompt injection.
  • Ingestion points: JSON results and metadata from Tenor and Giphy APIs.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this data as untrusted.
  • Capability inventory: Subprocess execution of the 'gifgrep' tool, 'jq' for JSON parsing, and filesystem write access via the download functionality.
  • Sanitization: No sanitization or validation of the fetched GIF metadata is described in the skill instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 9, 2026, 10:45 PM
Security Audit — agent-trust-hub — gifgrep