exiftool

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill frequently invokes shell commands to execute exiftool for reading, editing, and stripping metadata from files. It also uses standard utilities like file, mediainfo, and grep for file analysis and output filtering.
  • [EXTERNAL_DOWNLOADS]: The provided installation scripts (scripts/install.sh and scripts/install.ps1) utilize official system package managers, including Homebrew, APT, DNF, Pacman, and APK, to download and install the exiftool binary from trusted platform repositories.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and displaying untrusted data from external file metadata.
  • Ingestion points: Metadata extraction via exiftool <file> as described in SKILL.md and references/advanced-usage.md.
  • Boundary markers: None; metadata values are presented directly to the agent without delimiters or warnings to ignore embedded instructions.
  • Capability inventory: The skill has the ability to read and write to the file system and execute shell commands via exiftool and system package managers.
  • Sanitization: There is no evidence of sanitization or validation of the extracted metadata before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 04:18 PM
Security Audit — agent-trust-hub — exiftool