social-copy
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill operates as a structured content generation workflow without any detected malicious patterns, obfuscation, or data exfiltration attempts. All operations are confined to the local filesystem and intended skill logic.- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes external inputs such as campaign briefs, release facts, and media.
- Ingestion points: Reads campaign briefs, SOC deliverables, and release facts in the Workflow section of SKILL.md.
- Boundary markers: Includes an 'explicit no-invented-claims rule' and instructions to cite verified facts, though technical delimiters are not specified.
- Capability inventory: The skill is capable of writing to JSONL files (copy.jsonl, content_lineage.jsonl) and executing a local validation script (campaign_content.py).
- Sanitization: No explicit sanitization or filtering of input data is described.- [COMMAND_EXECUTION]: The workflow specifies that factual claims should be validated using a local script, campaign_content.py. This is a standard project-specific validation tool and does not represent an unauthorized command execution risk.
Audit Metadata