ads-competitor
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface where the agent processes untrusted text from external ad libraries. An attacker could craft ad copy that attempts to influence the agent's behavior during analysis.
- [INDIRECT_PROMPT_INJECTION]: Ingestion points: Analysis of competitor ad copy, creative messaging, and platforms (SKILL.md).
- [INDIRECT_PROMPT_INJECTION]: Boundary markers: None. No specific delimiters or instructions to ignore embedded commands are present in the guidelines.
- [INDIRECT_PROMPT_INJECTION]: Capability inventory: File-writing operations to generate markdown reports (COMPETITOR-INTELLIGENCE-REPORT.md, COMPETITIVE-GAPS.md).
- [INDIRECT_PROMPT_INJECTION]: Sanitization: The skill does not specify any sanitization or filtering logic for the ingested ad content.
Audit Metadata