social-media-specs
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to run a CLI tool using
npx social-media-specs, which downloads the package from the npm registry. The package is maintained by the skill author. - [COMMAND_EXECUTION]: Includes shell command examples to validate captions and media assets against platform-specific limits.
- [INDIRECT_PROMPT_INJECTION]: The CLI examples interpolate user-controlled text into shell commands, creating a surface for potential injection.
- Ingestion points: Untrusted data enters the agent context via the
<caption>and<ad text>arguments in theSKILL.mdcommand examples. - Boundary markers: The commands use double quotes for arguments but do not provide explicit instructions for the agent to sanitize shell-metacharacters from user-supplied strings.
- Capability inventory: The skill uses subprocess execution via
npxto run validation logic. - Sanitization: No sanitization or validation logic is defined for the input strings in the documentation.
Audit Metadata