social-repurpose
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and evaluation data with no executable scripts, binaries, or active logic.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external content such as transcripts and blog posts without sanitization or boundary markers.
- Ingestion points: The agent is instructed to ingest the full source (transcripts or blog posts) during the mining phase (SKILL.md).
- Boundary markers: Absent; there are no specified delimiters or instructions to treat the ingested source as data rather than instructions.
- Capability inventory: The skill's capabilities are limited to generating text drafts; it does not have access to the file system, network, or shell execution.
- Sanitization: Absent; the skill does not specify any validation or sanitization of the input source.
Audit Metadata