angle-finder
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in PROFILE mode which represents a standard attack surface.
- Ingestion points: LinkedIn profile URLs, screenshots, and pasted text (SKILL.md).
- Boundary markers: Absent; there are no explicit delimiters to separate untrusted profile data from the skill's instructions.
- Capability inventory: The skill uses the agent's capabilities to fetch URLs and generate text-based marketing strategies.
- Sanitization: Absent; the skill does not specify validation or sanitization for external content before analysis.
- [EXTERNAL_DOWNLOADS]: The skill fetches profile data from LinkedIn when a URL is provided. This is a legitimate functional requirement for a well-known service and is handled as a safe operation.
- [SAFE]: The skill does not contain any malicious patterns such as credential exfiltration, obfuscation, or privilege escalation. All operations are aligned with the primary purpose of campaign strategy generation.
Audit Metadata