figure-spec
Warn
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill calculates the path to the executable renderer script (
figure_renderer.py) at runtime by parsing a local file (.aris/installed-skills-codex.txt) and searching through multiple environment-dependent paths (~/.codex/, $ARIS_REPO). This dynamic path resolution can be subverted if an attacker modifies the configuration files. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates an automated review loop where user-influenced data (the FigureSpec JSON and SVG) is passed to a secondary AI agent (
spawn_agent). This creates an attack surface where malicious content embedded in the diagram labels or metadata could influence the behavior of the reviewer agent. - Ingestion points: Diagram descriptions are taken from
$ARGUMENTSand external files likePAPER_PLAN.mdto generate the JSON spec. - Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are included when passing the generated files to the reviewer agent.
- Capability inventory: The reviewer agent is granted high capabilities (e.g.,
gpt-6-astrawithxhighreasoning effort) and access to the rendered file paths. - Sanitization: While the renderer validates the JSON schema, it does not sanitize the semantic content of labels or metadata against instructional injections.
- [COMMAND_EXECUTION]: The skill explicitly uses the
Bashtool to executepython3for rendering and validation, andrsvg-convertfor PDF generation. These operations rely on the integrity of the dynamically resolved$FIGURE_RENDERERvariable.
Audit Metadata