ljg-invest
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including business plans (BP), founder conversation records, meeting notes, and pitch decks. These inputs serve as the primary source for the analysis report.
- Ingestion points: Materials provided by the user (BP, conversation records, meeting notes, pitch decks) in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters to treat the content of these external documents solely as data, which could lead the agent to follow malicious instructions embedded within the processed text.
- Capability inventory: The skill is authorized to use a 'Write' tool to save files to the local directory
~/Documents/notes/and a 'Research' tool to fetch external financial data. - Sanitization: The instructions do not define any sanitization, filtering, or escaping mechanisms for the external content before it is processed or written to disk.
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to use a 'Write' tool to save output to a specific local file system path (
~/Documents/notes/). While this is the primary intended function of the skill, it represents a direct interaction with the host file system.
Audit Metadata