alterlab-pra-media-planner
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by design as it is instructed to ingest data from potentially untrusted external files.\n
- Ingestion points: The workflow in SKILL.md explicitly directs the agent to "Read existing project files for context — campaign briefs, audience research, prior media plans, and budget parameters."\n
- Boundary markers: The skill lacks explicit boundary markers or instructions that would tell the agent to ignore or delimit embedded commands within the files it reads.\n
- Capability inventory: The agent has the capability to perform web searches, read local files, and write new markdown deliverables to the project directory, which could be abused if an injection is successful.\n
- Sanitization: There are no sanitization, validation, or filtering mechanisms described to handle the content of external files before processing.
Audit Metadata