social-campaign
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data which could lead to prompt injection attacks.
- Ingestion points: The skill reads external data from
../../references/SOCIAL_CAMPAIGN.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the workflow.
- Capability inventory: The skill has capabilities to write multiple files (
.json,.jsonl,.csv) and execute a Python script (scripts/promo_validate.py). - Sanitization: No sanitization or validation of the input markdown content is described before processing.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
scripts/promo_validate.py) to validate campaign data. This capability could be exploited if malicious instructions are injected into the campaign files being validated. - [DYNAMIC_EXECUTION]: The workflow relies on the execution of a pre-defined script (
scripts/promo_validate.py) which processes data generated from external references, creating a path for dynamic code behavior based on untrusted input.
Audit Metadata