signals-scout-ingestion-warnings
Signals scout for ingestion warnings — events and person/group updates that were dropped, mangled, or partially rejected during ingestion. Watches the warnings stream for new warning types, bursts above a type's own baseline, and error-severity clusters with broad reach, and files each actionable root cause as a report with the affected events and the fix.
60
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./products/signals/skills/signals-scout-ingestion-warnings/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt explicitly tells the agent to quote short snippets of untrusted, event-supplied "details" in reports (and notes that sample details may be arbitrary project-supplied values), which can force the LLM to echo secrets or API tokens verbatim if they appear in event data.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow calls `ingestion-warnings-list` and then reasons over “recent samples” including untrusted event-supplied fields like `details` (free text), which can be outsider-authored, and that text is ingested into the agent’s LLM context via the tool output used for reporting.
- Repository
- PostHog/posthog
- Commit
99982fd
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.