stage-tracker
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [DATA_EXFILTRATION]: The skill is designed to read and process business-sensitive documents, specifically
cap-table.md(equity and ownership data) andstartup-profile.md. It also describes functionality to synchronize this collected data with thechimeranext-api-consumeragent, moving local startup information to an external API endpoint owned by the vendor. - [COMMAND_EXECUTION]: The skill manages a local directory structure (
./launchpad/{startup-slug}/stage-tracker/) and automates the creation of several markdown artifacts, involving file system read and write operations. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from various sources to evaluate startup criteria.
- Ingestion points: Reads data from
startup-profile.md,cap-table.md, and multiple artifact directories such ascustomer-interview-system/andfounder-documents/. - Boundary markers: None identified; the skill does not use specific delimiters or instructions to ignore embedded commands in the processed data.
- Capability inventory: File system access (reading business data, writing markdown reports) and potential network operations via the API consumer agent.
- Sanitization: No explicit sanitization or validation of the ingested file content is mentioned.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata, without any accompanying executable scripts, binaries, or automated installation commands.
Audit Metadata