lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of repository content.
- Ingestion points: The instructions in
SKILL.mddirect the agent to 'analyze the codebase to understand the product' and its 'value proposition' when run from a project directory. - Boundary markers: Absent. There are no delimiters or instructions to ignore potential commands embedded within the code or documentation being analyzed.
- Capability inventory: The agent has the ability to perform web searches and generate personalized outreach strategies based on the ingested data.
- Sanitization: Absent. The skill does not implement any validation or filtering for the content it reads from the codebase.
- Risk: If the codebase contains untrusted data (such as third-party documentation, comments in external libraries, or community-contributed files), an attacker could embed malicious instructions that manipulate the agent's research results or lead outreach behavior.
Audit Metadata