pp-trendhunter
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install binaries from the author's repository on GitHub and the npm registry, including trendhunter-pp-cli and trendhunter-pp-mcp.
- [DATA_EXFILTRATION]: The tool includes a delivery feature via the --deliver flag that supports routing command output to a webhook: or file:. This provides a mechanism for sending data to external network endpoints or writing to the local filesystem.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it ingests and processes untrusted external data.
- Ingestion points: External content is ingested from TrendHunter.com trend cards, FAQ pages, and RSS feeds (processed in SKILL.md via the CLI).
- Boundary markers: Absent; there are no instructions to the agent to treat the scraped content as untrusted or to use delimiters.
- Capability inventory: The skill scripts can write to the filesystem and perform network POST requests using the --deliver feature.
- Sanitization: No explicit sanitization, validation, or filtering of the external HTML/JSON-LD content is described.
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands using the trendhunter-pp-cli binary via the Read Bash tool.
Audit Metadata