marketing-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features an "auto-draft" workflow that reads untrusted content from the local codebase (such as README files, landing page copy, and marketing assets) to generate a strategy document. This creates a surface for indirect prompt injection where an attacker could place malicious instructions in project files to influence the agent's behavior during the drafting process.
- Ingestion points: In
SKILL.md(Step 2), the agent is instructed to read the README, landing pages, marketing copy, about pages, and meta descriptions. - Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded prompts within the ingested data.
- Capability inventory: The skill utilizes file read operations across the repository and writes the output to
.agents/marketing-strategy.md. It does not demonstrate network exfiltration or arbitrary command execution capabilities. - Sanitization: There is no evidence of content sanitization, filtering, or validation before the ingested data is interpolated into the drafting prompt.
Audit Metadata