startup-validator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow involves executing 10-15 web searches and using
web_fetchto retrieve full articles from the internet. This untrusted data is then processed by the agent to generate reports, creating a surface for attackers to embed instructions in web content that could override agent behavior. - Ingestion points: Articles fetched from the web during the 'Comprehensive Market Research' phase as defined in SKILL.md.
- Boundary markers: Absent. The instructions do not provide the agent with delimiters or specific directives to ignore instructions found within the fetched research data.
- Capability inventory: The skill has the capability to read and write files on the local filesystem via the
scripts/market_analyzer.pytool. - Sanitization: No sanitization or filtering is performed on the content retrieved from web sources before it is analyzed by the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a bundled Python script (
scripts/market_analyzer.py) to perform quantitative analysis. This script interacts with the local filesystem by reading input JSON files and writing output result files, representing a capability that could be misused if the agent's context is compromised.
Audit Metadata