pm-competitor-deconstructor
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown files and reference guides intended to guide the AI's persona and analysis process. No malicious patterns, obfuscation, or unauthorized commands were detected.\n- [SAFE]: No executable code, scripts, or privilege escalation attempts are present in the skill files.\n- [SAFE]: The skill processes external data (competitor links, screenshots, and reports), which presents a theoretical surface for indirect prompt injection. However, this ingestion is necessary for the skill's primary function and no malicious exploitation was found. 1. Ingestion points: Competitor lists, links, and reports provided by the user (noted in SKILL.md). 2. Boundary markers: None. 3. Capability inventory: The skill defines no custom scripts or external tool calls. 4. Sanitization: None.
Audit Metadata