skills/amit-t/skills/wisdom-capture/Gen Agent Trust Hub

wisdom-capture

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources and scraping tools to synthesize content for the corpus.
  • Ingestion points: SKILL.md Step 2 (URL enrichment) and URL-IMPORT.md (scraped metadata, spoken-word transcripts from Whisper, and captions from Playwright).
  • Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the scraped text when performing analysis.
  • Capability inventory: The skill possesses file system write access (SKILL.md Step 7), network access via web tools, and git operation capabilities (SKILL.md Step 8, 9).
  • Sanitization: While basic formatting and whitespace cleaning are performed, there is no semantic sanitization of the content fetched from external URLs to prevent malicious prompts from influencing the agent's behavior during categorization or commit steps.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands that interpolate user-provided content.
  • Evidence: SKILL.md references the execution of wisdom_find_dup "$body" "$WISDOM_REPO" and git commit -m "..." which includes a preview of the body content.
  • Risk: A maliciously crafted wisdom snippet could potentially exploit shell command construction if the agent or environment does not properly escape special characters in the $body variable during the duplication check or commit process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 04:28 PM