specsfy-documentator
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
scripts/build_documentation.mjsusing the Node.js runtime. This script is bundled with the skill and is used to automate the scanning of the project directory and the generation of technical documentation. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads content from untrusted project files (such as
package.jsondescriptions,composer.jsonmetadata, and source code comments) and interpolates this data into the documentation. - Ingestion points: Files with extensions like
.js,.ts,.php,.py,.json, and lockfiles are read byscripts/build_documentation.mjs. - Boundary markers: The generated content is encapsulated within specific Markdown comment markers (
<!-- specsfy:documentator:start -->). - Capability inventory: The agent can read/write files and execute the provided analysis script.
- Sanitization: The script performs basic sanitization for Markdown tables by escaping pipe characters (
|) and stripping newlines from extracted strings, which mitigates simple injection attempts into the document structure.
Audit Metadata