content-analyzer
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external, untrusted content.
- Ingestion points: The skill primarily functions by ingesting and analyzing user-provided articles, tweets, and video transcripts.
- Boundary markers: There are no explicit delimiters (such as XML tags or unique markers) or specific instructions provided to the agent to disregard instructions potentially embedded within the analyzed content.
- Capability inventory: The skill uses standard web search for fact-checking and is instructed to save results to a local file (
analysis.md). It does not demonstrate capabilities for arbitrary command execution or unauthorized network exfiltration. - Sanitization: No input validation or content filtering is specified before the agent processes the external material.
Audit Metadata