power-analysis

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process untrusted external data (screenplay scenes), posing a risk of influencing agent behavior through embedded instructions. 1. Ingestion points: User-provided scenes processed via templates in SKILL.md. 2. Boundary markers: No delimiters or isolation warnings are present to separate the analysis instructions from input data. 3. Capability inventory: The skill lacks write/execute/network capabilities, limiting potential impact to internal reasoning. 4. Sanitization: No sanitization or validation of the input data is performed.
  • [NO_CODE] (INFO): No executable scripts, binaries, or package manager files (e.g., package.json, requirements.txt) are included in the skill.
  • [SAFE] (SAFE): No malicious patterns, obfuscation, or deceptive metadata were identified within the markdown documentation.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 07:14 AM