social-media-generator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate content and write files to the project directory. It lacks explicit sanitization or boundary markers to prevent embedded instructions in user input from potentially affecting the agent's behavior.
- Ingestion points: Event details, messages, and target audience gathered from the user in SKILL.md.
- Boundary markers: None identified; the agent is not instructed to use delimiters or ignore instructions within user-provided strings.
- Capability inventory: Creation of directory structures and writing markdown files to disk.
- Sanitization: No explicit validation or escaping of user input is specified for filenames or file content generation.
Audit Metadata