specstory-project-stats
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is configured to run a local Node.js script (scripts/get-stats.js) using the Bash tool to perform project identification and data retrieval.
- [DATA_EXFILTRATION]: The script reads project identifiers from .git/config or .specstory/.project.json and transmits a derived hash to the vendor's API at cloud.specstory.com. This behavior is documented and serves the skill's primary purpose of fetching remote statistics.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API (cloud.specstory.com) and presents it to the agent, creating a surface for potential instruction injection from the remote source.
- Ingestion points: API response body fetched in the fetchStats function within scripts/get-stats.js.
- Boundary markers: None present in the instructions to delimit external data from system prompts.
- Capability inventory: Execution of Node.js scripts via the Bash tool.
- Sanitization: The response is parsed as JSON but does not undergo additional validation or escaping before being presented to the agent.
Audit Metadata