marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read a local context file (".claude/product-marketing-context.md") to tailor marketing recommendations. This ingestion of external data creates a potential surface for indirect instructions to be processed by the agent.\n
- Ingestion points: Read operation for ".claude/product-marketing-context.md" specified in SKILL.md.\n
- Boundary markers: Absent. The skill does not explicitly warn the agent to ignore instructions embedded within this context file.\n
- Capability inventory: None. The skill contains no scripts, shell commands, or network operations that could be misused via injection.\n
- Sanitization: Absent. The skill relies on the platform's default handling of local context files.\n- [NO_CODE]: The skill consists entirely of Markdown instructions and reference documentation. It does not include any executable scripts, binaries, or automated shell commands, which significantly reduces the potential for privilege escalation, persistence, or data exfiltration.
Audit Metadata