researching-competitor-ads
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external advertisements which could theoretically contain malicious instructions.
- Ingestion points: Untrusted ad data is fetched via the
social_researchtool inSKILL.md(Step 3) andreferences/pulling-competitor-ads.md. - Boundary markers: Vision model prompts in
references/reading-one-ad.mduse a fixed narrative framework to structure the analysis, reducing the likelihood of the model obeying instructions within the ad content. - Capability inventory: The agent executes a local script
build_ledger.pyon the fetched data and uses vision tools (video_analysis,image_analysis) to interpret media content. - Sanitization: The
build_ledger.pyscript uses standard library JSON parsing and simple string normalization. - [COMMAND_EXECUTION]: The skill utilizes a local Python script to aggregate and process research data.
- Evidence:
SKILL.mdStep 4 executespython3 <skill-dir>/scripts/build_ledger.pyusing arguments derived from previous tool outputs.
Audit Metadata