event-social-media
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions and reference files. No executable scripts (.py, .js, .sh), binaries, or automated configuration files were detected within the skill package.
- [INDIRECT_PROMPT_INJECTION]: The skill features a data ingestion surface where it collects and processes user-provided event details through a multi-question interview.
- Ingestion points: User responses to the 11-question interview defined in the SKILL.md file.
- Boundary markers: Absent; the skill does not provide specific delimiters or instructions to the agent to disregard commands potentially embedded within user data.
- Capability inventory: None; the skill does not call or define any tools for network operations, file system access, or subprocess execution.
- Sanitization: Absent; there is no logic for validation or filtering of the user-provided interview responses.
- [CREDENTIALS_SAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in the skill metadata or instructions.
- [OBFUSCATION_SAFE]: No evidence of Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques was detected.
Audit Metadata