alterlab-pra-social-content
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest data from potentially untrusted sources which could contain malicious instructions.
- Ingestion points: The skill performs web searches for trending formats and algorithm updates, and reads local project files such as campaign briefs and analytics reports (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external data as untrusted or to ignore embedded instructions.
- Capability inventory: The agent has capabilities to read files, search the web, and write multiple types of markdown files directly to the project directory.
- Sanitization: There is no requirement or logic present for the agent to sanitize or validate content retrieved from external searches or project files before processing.
Audit Metadata