linkedin-prospect-research
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute
composioCLI commands. These commands are dynamically constructed using data provided by the user (prospect names, URLs) or data retrieved from the web. This creates a potential surface for command injection if the agent does not properly escape or sanitize these inputs before execution. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from LinkedIn profiles, recent posts, and web search results. Maliciously crafted content in a prospect's profile or posts could attempt to influence the agent's behavior.
- Ingestion points: LinkedIn profile metadata, user posts, and web search results (mentions, funding news).
- Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore embedded instructions within the research data.
- Capability inventory: The agent has access to
Bash(for CLI operations) andWrite(to save files to the./research/directory). - Sanitization: No sanitization or validation steps are defined for the data retrieved from external sources before it is used in report generation or CLI commands.
Audit Metadata