marketing-plan
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external client materials from the ~/marketing-plans/{client-slug}/materials/ directory during its research phase.
- Ingestion points: Step 1.2 of the methodology instructions requires the agent to read all available materials, including pitch decks, transcripts, and audit outputs provided by the user.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' wrappers when reading this content, potentially allowing malicious prompts within client files to influence agent behavior.
- Capability inventory: The skill has the capability to write files to the local file system and perform network operations via integrated tools such as Stripe, Ahrefs, and GitHub.
- Sanitization: No explicit sanitization or validation steps are prescribed for the content captured in the research record.
- [COMMAND_EXECUTION]: The skill instructions involve the use of shell commands for repository management and tool acquisition.
- Evidence: The 'FINALIZE' phase includes instructions for the agent to execute Git commands such as clone, commit, and push. Additionally, the operations stack mapping suggests the installation of the agent-browser package via npm.
Audit Metadata