social-graph-ranker
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is a purely instructional document defining a mathematical engine for bridge scoring and social graph traversal. It does not include any executable scripts (.py, .js, .sh), shell command triggers, or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a process that ingests external, untrusted social graph data from platforms like X and LinkedIn. This establishes a vulnerability surface where malicious instructions could be embedded in profile metadata or connection details.
- Ingestion points: The workflow involves pulling user graph data from X and LinkedIn (SKILL.md).
- Boundary markers: None provided in the skill body to separate data from instructions.
- Capability inventory: The skill itself contains no subprocess calls, file writes, or direct network operations; it provides the logic for the agent to use other existing tools (e.g.,
x-api). - Sanitization: No specific sanitization or filtering logic is defined for the ingested graph data.
Audit Metadata