content-factory
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill manages a pipeline that includes rendering video files (MP4) using the Remotion framework. This involves executing rendering commands based on generated content structures.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the Apify platform to scrape and analyze content from external URLs (social media reels). This process fetches data from the public internet into the agent's context for processing.
- [DATA_EXFILTRATION]: The skill is designed to send data (reels, captions, and direct messages) to Instagram via the Composio integration. While this is the intended functionality, it constitutes a pathway for data to leave the local environment to an external platform.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests untrusted data from the web to generate scripts.
- Ingestion points: External URLs provided by users and scraped via Apify (referenced in SKILL.md).
- Boundary markers: Absent; there are no specific delimiters or instructions for the agent to ignore potential instructions embedded in scraped reel transcripts.
- Capability inventory: Includes file system access (Remotion rendering), network operations (Instagram API calls via Composio), and interaction with local memory vaults (ai-brain).
- Sanitization: Not present; the skill does not specify validation or filtering of the content retrieved from external sources before using it to generate output.
Audit Metadata