product-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests untrusted data from external project files (README, landing pages, documentation, and
package.json) to auto-draft the marketing context. Maliciously crafted instructions within these project files could theoretically influence the agent's summarization behavior. - Ingestion points: Identified in
SKILL.md(Passo 2: Coletar Informação), where the agent is instructed to read various repository files. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these files.
- Capability inventory: The skill uses file reading capabilities to gather context and performs file writes to save the
.agents/product-marketing.mddocument. - Sanitization: There is no evidence of content sanitization or validation for the data ingested from the repository files.
Audit Metadata