cro-investor-relations
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of untrusted data without security boundaries.
- Ingestion points: Company context, fundraising goals, and market data inputs defined in SKILL.md.
- Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are present.
- Capability inventory: Automated outreach sequences, calendar orchestration, and due diligence data room staging.
- Sanitization: No input validation or filtering of external content is specified.
- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized network operations were identified.
- [NO_CODE]: The skill consists of high-level orchestration instructions and markdown templates; it does not contain executable scripts, binaries, or command-line operations.
- [DATA_EXFILTRATION]: While the skill manages highly sensitive data (ARR, burn, cap tables), there are no instructions or commands that exfiltrate this data to unauthorized external destinations.
- [COMMAND_EXECUTION]: No shell commands, system calls, or subprocess executions are defined in the orchestration phases.
Audit Metadata