linkedin-post-writer
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and draft ideas to generate social media content.\n
- Ingestion points: As described in
SKILL.md, the skill takes 'Topic', 'angle', and 'draft ideas' directly from the user and loads data fromstory-bank.mdandvoice-profile.md.\n - Boundary markers: The instructions do not define clear delimiters or protective framing (such as XML tags or specific markdown blocks) to isolate untrusted user input from agent instructions during the drafting process.\n
- Capability inventory: The skill possesses the capability to publish content to external social media platforms via the
lib.publishtool and generate images vialib.illustrate.\n - Sanitization: While the skill performs a 'Humanizer pass' and an 'Audit' mode to check for linguistic quality and AI-like phrasing, it lacks a dedicated security sanitization layer to detect or neutralize malicious instructions embedded in the input data.
Audit Metadata