specsfy-update-spec
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Node.js script (
analyze_change.mjs) and Git commands to analyze changes between the current working tree and the Git repository. These actions are performed locally on project files and are necessary for the skill's purpose of managing specification lifecycles. - [DATA_EXPOSURE]: The skill reads project configuration files and specifications from the local directory (e.g.,
PROJECT.md,.specsfy/RULES.md). This access is within the scope of its task to maintain project consistency and does not involve sensitive system-level files, credentials, or external data transmission. - [INDIRECT_PROMPT_INJECTION]: The skill processes markdown files that may contain untrusted data, which could influence the agent's workflow.
- Ingestion points:
specs/<estado>/<NNNN>-<slug>/spec.md,PROJECT.md,.specsfy/STACK.md,.specsfy/RULES.md, and.specsfy/DATABASE.md(all project-level files). - Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore content embedded in these files.
- Capability inventory: Subprocess calls to
git, local script execution (analyze_change.mjs), and file reading/writing within the project folder. - Sanitization: Absent. The provided Node.js script performs string normalization for parsing but does not sanitize the content to prevent adversarial prompt instructions from influencing the agent's logic.
Audit Metadata