cap-table
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's logic is entirely dedicated to its stated purpose of managing equity and dilution scenarios. No evidence of malicious behavior, such as unauthorized network requests or credential harvesting, was found.
- [NO_CODE]: This skill is implemented as a set of markdown instructions and metadata. It does not include any Python scripts, Node.js packages, or binary executables.
- [PROMPT_INJECTION]: The skill processes external data through ingestion points. Ingestion points: Reads
data/cfo/cap_table.json,data/cfo/latest_forecast.json, anddata/cfo/fundraise_plan.json(SKILL.md). Boundary markers: No delimiters or warnings are used to isolate untrusted data. Capability inventory: The skill only performs calculations and generates markdown tables; it lacks dangerous capabilities like subprocess execution or network access. Sanitization: No input validation or filtering of the file contents is performed. While this represents a surface for indirect prompt injection, it is the intended primary functionality of the skill.
Audit Metadata