linkedin-content-planner
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from a story bank JSON file which is then interpolated into the plan output. This represents a potential surface for indirect prompt injection if the data source contains malicious instructions intended for the agent.
- Ingestion points: Data is ingested from user-provided files such as
assets/sample_story_bank.jsonvia thescripts/plan_builder.pyscript. - Boundary markers: The skill uses markdown templates to structure the output but does not include explicit warnings to the agent regarding the untrusted nature of the story bank content.
- Capability inventory: The
plan_builder.pyscript possesses capabilities for local file reading and standard output. - Sanitization: Text content from the story bank entries is not validated or sanitized before interpolation into the final plan.
Audit Metadata