caveman-compress

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external programs to perform text processing. It invokes the 'claude' CLI utility through the Python subprocess module. Evidence includes subprocess.run(["claude", "--print"], ...) in scripts/compress.py. The skill also defines a command-line trigger in SKILL.md that executes a Python module and passes file paths as arguments.
  • [PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by reading external file content and inserting it into prompts for an LLM without adequate sanitization or robust delimiters.
  • Ingestion points: The skill reads target files using Path.read_text() in scripts/compress.py.
  • Boundary markers: Prompt templates in scripts/compress.py use weak markers like 'TEXT:' and 'ORIGINAL:' which can be bypassed by malicious content within the files.
  • Capability inventory: The skill possesses the ability to read from and write to the filesystem, and to execute external processes.
  • Sanitization: No sanitization or escaping of the ingested text is performed before prompt construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 05:18 PM