skills/adryanmoldokkr32-pixel/bionicbot-giant-sovereign-skills/narrative-manipulation-control/Gen Agent Trust Hub
narrative-manipulation-control
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to deploy 'Mirror Stories' that appear organic while reflecting user goals. This represents a request to use the AI for the creation and dissemination of deceptive or manipulative content, which may violate safety guidelines regarding truthfulness and disinformation.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8). Ingestion points: The agent is instructed to monitor over 100 global news and social media sources (SKILL.md). Boundary markers: There are no instructions to use delimiters or warnings to ignore instructions embedded in the processed external data. Capability inventory: The skill mentions 'deploying' stories, which implies a capability to publish or transmit content to external platforms (SKILL.md). Sanitization: No mechanisms for filtering, validating, or escaping data from external sources are mentioned.
- [NO_CODE]: The skill is composed entirely of natural language instructions in a markdown file and does not include executable scripts or third-party package dependencies.
Audit Metadata