content-media-plan
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to check for the presence of the
infshCLI tool and to run image generation tasks using thefalai/flux-dev-loramodel.- [EXTERNAL_DOWNLOADS]: The agent is directed to fetch and process data from external websites and multiple social media platforms (Instagram, TikTok, Facebook, YouTube) provided by the user using various scraping tools.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external sources without sufficient isolation. - Ingestion points: Scraping of brand websites via
FirecrawlScrapeTooland social media profiles viaSocial Toolkit MCP. - Boundary markers: The instructions lack explicit delimiters or 'ignore' directives to separate scraped content from the agent's core logic.
- Capability inventory: The skill has the ability to write to the local file system, interact with the Notion API, and execute shell commands via the
infshCLI. - Sanitization: No sanitization or validation of the retrieved web content is performed before it is used to generate the brand strategy and content hooks.
Audit Metadata