newsletter-sponsorship-finder

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized command execution were detected. The skill performs its described intelligence-gathering function using standard methods.- [EXTERNAL_DOWNLOADS]: The helper script scripts/search_newsletters.py uses the requests library to fetch publication data from the Substack API (substack.com). This is a well-known service and the data retrieved is public metadata necessary for the skill's discovery process.- [DATA_EXFILTRATION]: Network operations are restricted to querying the Substack API and performing web searches for public newsletter information. No sensitive local data, environment variables, or user credentials are accessed or transmitted.- [PROMPT_INJECTION]: The skill ingests untrusted data from external sources to generate reports. \n
  • Ingestion points: Newsletter names and descriptions retrieved from the Substack API and WebSearch results (documented in scripts/search_newsletters.py and SKILL.md). \n
  • Boundary markers: None present in the prompt instructions to delimit external content. \n
  • Capability inventory: Writing findings to a markdown report file as described in the Output phase of SKILL.md. \n
  • Sanitization: No explicit sanitization or filtering of external text is performed before it is included in the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:02 PM