specsfy-specialist-astro
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from Markdown, MDX, and external CMS sources, creating an indirect prompt injection surface. This is mitigated by the skill's requirement for strict Zod schema validation at the ingestion boundary.
- Ingestion points: Markdown files, MDX files, and CMS remote content referenced in SKILL.md and standards.md.
- Boundary markers: The skill instructs the agent to treat invalid frontmatter as a build error rather than tolerated data.
- Capability inventory: Invocation of
astro checkandastro buildCLI tools. - Sanitization: Mandatory use of Zod schemas to validate all content and route parameters.
- [COMMAND_EXECUTION]: The skill requires the agent to execute standard framework CLI tools for validation and building.
- Evidence: Instructions to run
astro checkand production builds in the Validation section of SKILL.md.
Audit Metadata