profile-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests potentially untrusted data from a local project file ('about-me.md') and user-supplied LinkedIn profile content (text or screenshots). This creates a vulnerability surface for indirect prompt injection, where malicious instructions could be embedded in the profile data. However, the risk is minimal as the skill lacks high-privilege capabilities such as network access or shell execution.
- Ingestion points: Reads 'about-me.md' and processes user-provided profile text or files.
- Boundary markers: The skill does not use explicit delimiters or specific instructions to the agent to ignore embedded commands in the source data.
- Capability inventory: The skill is limited to generating text copy and image prompts; it has no access to network, file writing, or command execution tools.
- Sanitization: No sanitization or validation of the ingested content is performed.
Audit Metadata