comments-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external social media comments.\n
- Ingestion points: Untrusted comment data enters the agent context via API endpoints such as
app/v3/fetch_video_comments,v2/fetch_post_comments, andweb_v2/get_video_commentsas described in the Workflow section ofSKILL.md.\n - Boundary markers: The instructions do not specify any delimiters (e.g., XML tags) or instructions to the agent to disregard instructions potentially embedded within the fetched comments.\n
- Capability inventory: The skill is designed for analysis and summarization; it does not explicitly define file-system or shell command execution on the processed data.\n
- Sanitization: There is no mention of content sanitization or filtering of the fetched comment data before it is presented to the agent for analysis.
Audit Metadata