skills/terrylica/cc-skills/play/Gen Agent Trust Hub

play

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external .cast recording files provided via the file argument.
  • Ingestion points: The agent reads and searches for .cast files using the Glob and Bash tools.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed files.
  • Capability inventory: The skill has access to Bash, Glob, and AskUserQuestion tools.
  • Sanitization: No sanitization or validation of the content within the .cast files is specified before the agent acts upon them.
  • [DYNAMIC_EXECUTION]: The skill instructions include a 'Self-Evolving' section and 'Post-Execution Reflection' that explicitly direct the agent to modify the SKILL.md file to fix issues or update parameters.
  • This self-modification mechanism allows for the dynamic alteration of the skill's logic at runtime, which could be leveraged to introduce malicious instructions if the agent's reasoning is influenced by adversarial input.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 02:12 AM