sf-report
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several Node.js scripts (e.g., status.mjs, render-work-report.mjs) located in the local
.specforge/core/scripts/directory to generate reports. - [COMMAND_EXECUTION]: The instruction to run
node .specforge/core/scripts/render-work-report.mjs --work-item <work-id>uses a user-supplied variable. If this input is not strictly validated or sanitized by the agent, it creates a risk of command injection (e.g., appending shell operators to the ID). - [PROMPT_INJECTION]: The skill processes untrusted data in the form of markdown artifacts (requirements, UI designs, technical plans) to generate the HTML report. This presents an indirect prompt injection surface where malicious instructions embedded in these files could influence the agent's behavior during the generation process.
- Ingestion points: Markdown files stored within the
.specforge/directory. - Boundary markers: None identified; the skill treats markdown content as the "source of truth" for the report.
- Capability inventory: The skill can execute local shell commands via Node.js scripts and read project files.
- Sanitization: No evidence of content sanitization or instruction filtering for the processed markdown data.
Audit Metadata