vader-sentiment-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process social media and user-generated text, which constitutes an indirect prompt injection surface (Category 8).
- Ingestion points: The skill ingests untrusted data from the 'title' and 'body' fields of input records, as demonstrated in the 'score_multi_tier' function in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters (like triple backticks) or explicit 'ignore embedded instructions' warnings when the agent processes the external text.
- Capability inventory: The skill's scripts are focused on data analysis and sentiment scoring; no high-privilege capabilities such as arbitrary command execution, file system writes, or network exfiltration are present.
- Sanitization: The 'vader_safe_preprocess' function performs basic cleaning of URLs, mentions, and HTML tags, but does not provide robust sanitization against prompt injection payloads.
Audit Metadata