outlier-post-finder
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from various social media platforms (including TikTok, Instagram, and YouTube) to identify content outliers and patterns. This creates an attack surface for indirect prompt injection.
- Ingestion points: Data is fetched through multiple external endpoints listed in SKILL.md, including post details, transcripts, and comments.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing transcripts or external content.
- Capability inventory: The skill allows the use of Bash, Read, Write, and WebFetch tools, which increases the potential impact of a successful injection.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate external text data before analysis or report generation.
Audit Metadata