ll
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands for task verification and validation, such as checking word counts or searching for patterns in generated files.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted external data (articles, tweets, and source documents) to drive its autonomous loops without explicit sanitization or boundary markers.
- Ingestion points: Processes manifesto content, source documents, articles, and social media data from the project directory (SKILL.md).
- Boundary markers: None identified in the provided prompt templates.
- Capability inventory: Uses Bash, Write, and Agent tools to execute tasks and shell commands based on loop state.
- Sanitization: No explicit sanitization or filtering of ingested content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill references the 'claude-agent-sdk' as an execution adapter, implying dependency on external libraries for operation.
Audit Metadata