startup-business-analyst-business-case
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection (Category 8) as it is designed to ingest and analyze external materials such as pitch decks and market research data.
- Ingestion points: The skill uses the
Readtool to access user documents andWebFetchto retrieve web content (SKILL.md). - Boundary markers: No delimiters or instructions to ignore embedded commands are specified in the document structure.
- Capability inventory: The skill utilizes
Bash,Write,WebFetch, andEdittools (SKILL.md). - Sanitization: There is no evidence of input validation or content filtering for the data being processed.
- [COMMAND_EXECUTION]: The skill requests permission to use the
Bashtool. While no malicious shell scripts are included in the definition, granting shell access to an agent that processes untrusted external content increases the potential impact of a prompt injection attack. - [EXTERNAL_DOWNLOADS]: The skill employs
WebSearchandWebFetchto gather information from external domains. Although used here for legitimate market analysis, these capabilities could be misused for data exfiltration if the agent's instructions were compromised.
Audit Metadata