instagram-lead-parser
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from public Instagram profiles (bios, posts, and search results). This presents a surface for indirect prompt injection where malicious instructions embedded in a creator's bio could attempt to influence the agent's evaluation or approval process.
- Ingestion points: Instagram profile URLs, bios, and post content are processed to extract metrics and evidence (referenced in
SKILL.mdandreferences/evidence-policy.md). - Boundary markers: The skill utilizes extensive human review requirements and documentation policies to verify evidence, but does not use explicit prompt delimiters for the ingested content itself.
- Capability inventory: The skill executes a local Python validator (
scripts/validate_batch.py) and performs file-writing operations for CSV generation. - Sanitization: The skill employs a deterministic validation script to enforce schema and metric consistency, which mitigates data corruption but does not prevent logic-based prompt injection.
Audit Metadata