prompt-personagem

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/prompt.py) to generate randomized character prompts. The script is self-contained, using only standard Python libraries (random, textwrap) and a local data file (scripts/listas.py). There is no evidence of arbitrary command execution or shell injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user triggers via the /personagem command.
  • Ingestion points: User command input triggers the script execution.
  • Boundary markers: The SKILL.md includes explicit guardrails to prevent users from attempting to modify lists through chat or requesting inappropriate content.
  • Capability inventory: The skill executes local Python code and generates text output based on internal lists.
  • Sanitization: The generated output is composed solely of attributes selected from pre-defined, static lists in scripts/listas.py, which effectively isolates the prompt generation from potentially malicious user-provided text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:24 PM
Security Audit — agent-trust-hub — prompt-personagem